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. 76420
    Prev
    Next
    INDEX
    Explanations

    excel formulas

    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
    ضرار
    -0.09
     auditors
    -0.08
    معدات
    -0.08
     nars
    -0.08
    لاع
    -0.08
    avors
    -0.08
    ocê
    -0.08
     بلغت
    -0.07
    amál
    -0.07
     þær
    -0.07
    POSITIVE LOGITS
     ж
    0.08
     ans
    0.08
    Inp
    0.07
     преиму
    0.07
     criterion
    0.07
    Expr
    0.07
     സംവിധാനം
    0.07
    ('',
    0.07
    (expr
    0.07
    nation
    0.07
    Activations Density 0.001%

    No Known Activations