AI RESEARCH
One Language, Two Scripts: Probing Script-Invariance in LLM Concept Representations
arXiv CS.CL
•
ArXi:2603.08869v1 Announce Type: new Do the features learned by Sparse Autoencoders (SAEs) represent abstract meaning, or are they tied to how text is written? We investigate this question using Serbian digraphia as a controlled testbed: Serbian is written interchangeably in Latin and Cyrillic scripts with a near-perfect character mapping between them, enabling us to vary orthography while holding meaning exactly constant. Crucially, these scripts are tokenized completely differently, sharing no tokens whatsoever.