SharedSAE: One Feature Dictionary Across Language Models
SharedSAE: One Feature Dictionary Across Language Models
Deep Dive
Computer Science > Machine Learning arXiv:2609.04344 (cs) [Submitted on 3 Sep 2026] Title: SharedSAE: One Feature Dictionary Across Language Models Authors: Daniil Ognev , Célian Vasson , Lijie Hu , Kentaro Inui , Benjamin Heinzerling View a PDF of the paper titled SharedSAE: One Feature Dictionary