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

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 54451
    Prev
    Next
    INDEX
    Explanations

    чем

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    料
    -0.08
     ನಡೆಸ
    -0.08
     ஆச
    -0.08
    掲
    -0.08
     همیشه
    -0.08
     உர
    -0.08
    MLE
    -0.08
     copyrighted
    -0.07
     gec
    -0.07
    ruck
    -0.07
    POSITIVE LOGITS
     differences
    0.11
     отличие
    0.11
     Unterschiede
    0.10
    Difference
    0.10
     difference
    0.10
     differs
    0.10
    Dif
    0.09
    区别
    0.09
     Differences
    0.09
    _difference
    0.09
    Activations Density 0.003%

    No Known Activations