© 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. 3-RESID-POST-AA
    11. 1524
    Prev
    Next
    INDEX
    Explanations

    Math operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brook
    -0.08
     botan
    -0.08
    CID
    -0.08
     FAC
    -0.07
     Belle
    -0.07
     Pearl
    -0.07
     Hubert
    -0.07
     CCC
    -0.07
     pearl
    -0.07
    Chess
    -0.07
    POSITIVE LOGITS
     Dyn
    0.08
    ища
    0.08
     �
    0.08
     segue
    0.07
    .Multi
    0.07
    .agent
    0.07
    401
    0.07
    .Lerp
    0.07
    探索
    0.07
    这一
    0.07
    Activations Density 0.265%

    No Known Activations