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. 15-RESID-POST-AA
    6. 19325
    Prev
    Next
    INDEX
    Explanations

    code, numbers, instructions

    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
    uding
    -0.09
    anding
    -0.08
    keiten
    -0.08
    iland
    -0.08
    e
    -0.08
    licting
    -0.08
    for
    -0.08
    assem
    -0.08
    mdl
    -0.08
     it
    -0.07
    POSITIVE LOGITS
     especiales
    0.09
    .MAX
    0.09
    ,password
    0.08
     ನಿವಾಸ
    0.08
    帮
    0.08
    )،
    0.08
    ิเศษ
    0.08
     nigba
    0.08
     xüsusi
    0.08
     cliënten
    0.08
    Activations Density 0.000%

    No Known Activations