GALICHIN, A. V.; DONTSOV, A.; DRUZHININA, P.; RAZZHIGAEV, A.; ROGOV, O.; TUTUBALINA, E.; OSELEDETS, I. I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 36, p. 30771-30779, 2026. DOI: 10.1609/aaai.v40i36.40334. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40334. Acesso em: 30 apr. 2026.