TSAE: Structured Sparse Autoencoders for Interpreting Time-Series Forecasting Models

Excerpt

arXiv:2610.04925v1 Announce Type: cross Abstract: Time-series forecasting informs critical decisions in energy dispatch, industrial operations, and environmental monitoring; understanding the patterns models rely on is essential for assessing reliability and identifying failures. Input attribution identifies important variables and time segments but offers limited insight into internal features, while standard sparse autoencoder (SAE) objectives do not directly constrain cross-variable structure