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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 120370
    Prev
    Next
    INDEX
    Explanations

    lists

    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
     చూప
    -0.08
     isk
    -0.08
     malt
    -0.08
     multiline
    -0.08
    отов
    -0.08
     malformed
    -0.08
     čas
    -0.08
     showed
    -0.08
     acert
    -0.07
     tatu
    -0.07
    POSITIVE LOGITS
     newsletters
    0.09
    .live
    0.08
     Publ
    0.08
    ython
    0.08
    传媒
    0.08
     yayın
    0.08
    ினர்
    0.08
     firing
    0.08
     membership
    0.08
    itant
    0.08
    Activations Density 0.006%

    No Known Activations