© 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. 12895
    Prev
    Next
    INDEX
    Explanations

    row

    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
     Gentleman
    -0.08
    z
    -0.08
    zne
    -0.08
    .Repositories
    -0.08
     ગુણ
    -0.08
     taun
    -0.08
     Isl
    -0.07
    (classes
    -0.07
     wagen
    -0.07
    เ
    -0.07
    POSITIVE LOGITS
    atcher
    0.08
    adio
    0.08
    大小
    0.08
    ulk
    0.07
    ults
    0.07
     территория
    0.07
    0.07
     HOT
    0.07
     לשל
    0.07
     NEXT
    0.07
    Activations Density 0.001%
    No Known Activations