Can Rager

Independent, None

Joined

October 2023

Names

Can Rager (Preferred)

Emails

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Independent

None (other.su)

2022 – 2026

Undergrad student

Physics, Universität Innsbruck (uibk.ac.at)

2019 – 2022

Advisors, Relations & Conflicts

No relations added

Expertise

interpretability

Present

alignment

Present

editing

,

steering

Present

Publications

Priors in time: Missing inductive biases for language model interpretability
Ekdeep Singh Lubana, Can Rager, Sai Sumedh R. Hindupur, Valérie Costa, Oam Patel, Sonia Krishna Murthy, Thomas Fel, Greta Tuckute, Daniel Wurgaft, Eric Bigelow, Demba E. Ba, Melanie Weber, Aaron Mueller
- ICLR 2026 Poster
- Readers: Everyone
Discovering Forbidden Topics in Language Models
Can Rager, Chris Wendler, Rohit Gandikota, David Bau
- Submitted to ICLR 2026
- Readers: Everyone
Priors in Time: A Generative View of Sparse Autoencoders for Sequential Representations
Ekdeep Singh Lubana, Sai Sumedh R. Hindupur, Can Rager, Valérie Costa, Oam Patel, Sonia Krishna Murthy, Thomas Fel, Greta Tuckute, Daniel Wurgaft, Demba E. Ba, Melanie Weber, Aaron Mueller
- CogInterp @ NeurIPS 2025 Poster
- Readers: Everyone
Automatically Finding Rule-Based Neurons in OthelloGPT
Aditya Singh, Zihang Wen, Srujananjali Medicherla, Adam Karvonen, Can Rager
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
Adam Karvonen, Can Rager, Johnny Lin, Curt Tigges, Joseph Isaac Bloom, David Chanin, Yeu-Tong Lau, Eoin Farrell, Callum Stuart McDougall, Kola Ayonrinde, Demian Till, Matthew Wearden, Arthur Conmy, Samuel Marks, Neel Nanda
- ICML 2025 poster
- Readers: Everyone
NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
Jaden Fried Fiotto-Kaufman, Alexander Russell Loftus, Eric Todd, Jannik Brinkmann, Koyena Pal, Dmitrii Troitskii, Michael Ripa, Adam Belfki, Can Rager, Caden Juang, Aaron Mueller, Samuel Marks, Arnab Sen Sharma, Francesca Lucchetti, Nikhil Prakash, Carla E. Brodley, Arjun Guha, Jonathan Bell, Byron C Wallace, David Bau
- ICLR 2025 Poster
- Readers: Everyone
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
Samuel Marks, Can Rager, Eric J Michaud, Yonatan Belinkov, David Bau, Aaron Mueller
- ICLR 2025 Oral
- Readers: Everyone
Attribution Patching Outperforms Automated Circuit Discovery
Aaquib Syed, Can Rager, Arthur Conmy
- BlackboxNLP 2024
- Readers: Everyone
An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L
Jett Janiak, Can Rager, James Dao, Yeu-Tong Lau
- BlackboxNLP 2024
- Readers: Everyone
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
Adam Karvonen, Benjamin Wright, Can Rager, Rico Angell, Jannik Brinkmann, Logan Riggs Smith, Claudio Mayrink Verdun, David Bau, Samuel Marks
- ICML 2024 MI Workshop Oral
- Readers: Everyone

View all 13 publications

Co-Authors

View all 68 co-authors