© 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. 99275
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     Herzog
    -0.07
    Ki
    -0.07
     choć
    -0.07
     today
    -0.07
     feng
    -0.07
     sicherlich
    -0.07
     назв
    -0.07
     hopefully
    -0.07
     avi
    -0.07
    ựa
    -0.07
    POSITIVE LOGITS
     speciale
    0.13
    special
    0.13
     special
    0.13
    特殊
    0.13
    .special
    0.12
     supplémentaire
    0.12
    额
    0.12
     특별
    0.12
     spéciale
    0.12
     zusätzlich
    0.11
    Activations Density 0.036%

    No Known Activations