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. 58567
    Prev
    Next
    INDEX
    Explanations

    bank

    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
     ether
    -0.08
     madh
    -0.08
     avi
    -0.08
    ,还有
    -0.08
     equiv
    -0.08
    迷
    -0.07
    付
    -0.07
     pher
    -0.07
     gase
    -0.07
     qədər
    -0.07
    POSITIVE LOGITS
    Dados
    0.08
     climate
    0.08
    .columns
    0.08
     loan
    0.08
    columns
    0.07
     hus
    0.07
    融资
    0.07
    Coll
    0.07
     Climate
    0.07
    085
    0.07
    Activations Density 0.002%

    No Known Activations