© 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. 75470
    Prev
    Next
    INDEX
    Explanations

    mass

    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
     état
    -0.09
     états
    -0.08
    oji
    -0.08
     одного
    -0.08
     mins
    -0.08
     foliage
    -0.08
     свой
    -0.07
     root
    -0.07
    -être
    -0.07
    穿
    -0.07
    POSITIVE LOGITS
    ု
    0.08
     Libr
    0.08
     Α
    0.08
     discrep
    0.07
    tablename
    0.07
     Numer
    0.07
    (Position
    0.07
    Matthew
    0.07
     Numeric
    0.07
     .↵↵
    0.07
    Activations Density 0.002%

    No Known Activations