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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 130061
    Prev
    Next
    INDEX
    Explanations

    CADE

    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
    ılmış
    -0.08
    unning
    -0.07
     evokes
    -0.07
     Jens
    -0.07
     swollen
    -0.07
    byg
    -0.07
     steals
    -0.07
    agon
    -0.07
     koko
    -0.07
     출
    -0.07
    POSITIVE LOGITS
     Auth
    0.08
     Attr
    0.08
    .Term
    0.08
     Referential
    0.08
    (Action
    0.08
    -await
    0.07
     استقبال
    0.07
     Associations
    0.07
     Fixture
    0.07
    кес
    0.07
    Activations Density 0.000%

    No Known Activations