© 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. 15-RESID-POST-AA
    11. 16409
    Prev
    Next
    INDEX
    Explanations

    software/web errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     жардам
    -0.09
    ակալ
    -0.09
    ованию
    -0.09
     կարելի
    -0.09
     նկատ
    -0.09
     որոնք
    -0.09
     жакшы
    -0.09
    �รดิต
    -0.09
     կյանքի
    -0.09
     վերաբ
    -0.09
    POSITIVE LOGITS
     is
    0.09
    ,
    0.09
    .↵
    0.08
    ↵
    0.08
    .
    0.08
     are
    0.07
     instead
    0.07
     (
    0.07
     '
    0.07
    —as
    0.07
    Activations Density 0.019%

    No Known Activations