TimeSAE: Sparse Decoding for Faithful Explanations of Black-Box Time Series Models

ICLR 2026 Conference Submission19695 Authors

Keywords: Time series interpretation, counterfactual explanations, black-box models

Abstract: As black box models and pretrained models gain traction in time series applications, understanding and explaining their predictions becomes increasingly vital, especially in high-stakes domains where interpretability and trust are essential. However, most of the existing methods involve only in-distribution explanation, and do not generalize outside the training support, which requires the learning capability of generalization. In this work, we aim to provide a framework to explain black-box models for time series data through the dual lenses of Sparse Autoencoders (SAEs) and causality. We show that many current explanation methods are sensitive to distributional shifts, limiting their effectiveness in real-world scenarios. Building on the concept of Sparse Autoencoder, we introduce TimeSAE, a framework for black-box model explanation. We conduct extensive evaluations of TimeSAE on both synthetic and real-world time series datasets, comparing it to leading baselines. The results, supported by both quantitative metrics and qualitative insights, show that \modelname delivers more faithful and robust explanations. Our code is available in an easy-to-use library TimeSAE-Lib: https://anonymous.4open.science/w/TimeSAE-571D/

Primary Area: interpretability and explainable AI

Submission Number: 19695