© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 99383
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    Literal
    -0.08
     pocket
    -0.08
    Kid
    -0.08
     leftovers
    -0.08
    Expressions
    -0.08
    Mono
    -0.08
    EDIT
    -0.08
    Expression
    -0.07
    Legacy
    -0.07
     Literal
    -0.07
    POSITIVE LOGITS
     познаком
    0.09
     establish
    0.08
     Соз
    0.08
     steps
    0.08
     Determine
    0.08
     확보
    0.08
     lấy
    0.08
    .seed
    0.08
     langkah
    0.08
     환경
    0.08
    Activations Density 0.019%

    No Known Activations