© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 20718
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     across
    -0.09
     Tanto
    -0.09
    .Mode
    -0.09
     both
    -0.09
    ôsob
    -0.08
     zarówno
    -0.08
    ability
    -0.08
    -format
    -0.08
     atât
    -0.08
    ables
    -0.08
    POSITIVE LOGITS
    ？↵↵
    0.09
     निधन
    0.08
     familial
    0.08
    ?!↵↵
    0.08
     garagem
    0.08
    ):-
    0.08
     RETURNS
    0.08
     μας
    0.07
    )?↵↵
    0.07
     hefur
    0.07
    Activations Density 0.001%

    No Known Activations