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. 42418
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    .runtime
    -0.09
    .properties
    -0.08
     সংক
    -0.08
    .preferences
    -0.08
    .bean
    -0.08
    packs
    -0.08
    isions
    -0.08
     సంక
    -0.08
     anemia
    -0.08
    ammable
    -0.08
    POSITIVE LOGITS
    Photography
    0.08
     dä
    0.08
     downright
    0.07
     cet
    0.07
     overleden
    0.07
    CLE
    0.07
     کوئی
    0.07
     CEO
    0.07
    ува
    0.07
     "`
    0.07
    Activations Density 0.009%

    No Known Activations