Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12974
    Prev
    Next
    INDEX
    Explanations

    colon

    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
    UBLISH
    -0.09
     judiciaire
    -0.08
     grap
    -0.08
     высокого
    -0.08
    .gener
    -0.08
     треб
    -0.08
     judicia
    -0.08
    YCLE
    -0.08
     ગ્ર
    -0.08
     освоб
    -0.07
    POSITIVE LOGITS
     "..
    0.08
     mam
    0.08
    -worthy
    0.07
     "",↵
    0.07
     isso
    0.07
     noun
    0.07
     lama
    0.07
    ्यात
    0.07
     dei
    0.07
     clich
    0.07
    Activations Density 0.005%

    No Known Activations