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. 88287
    Prev
    Next
    INDEX
    Explanations

    Instructions and guidelines

    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
    上市
    -0.11
    营销
    -0.09
    的邀请码
    -0.09
     carré
    -0.09
    dropdown
    -0.09
     discriminatory
    -0.08
    Counts
    -0.08
    commercial
    -0.08
    sortable
    -0.08
    ెట
    -0.08
    POSITIVE LOGITS
     pogod
    0.08
     Sleep
    0.08
     Germ
    0.08
    adian
    0.07
     rehears
    0.07
    lain
    0.07
     reparación
    0.07
     fragile
    0.07
     thirst
    0.07
     സമയം
    0.07
    Activations Density 0.001%

    No Known Activations