© 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. 1472
    Prev
    Next
    INDEX
    Explanations

    code

    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
     kut
    -0.10
     Haush
    -0.08
    (mysqli
    -0.07
     â
    -0.07
     Kobo
    -0.07
    adaptive
    -0.07
     இட
    -0.07
     rech
    -0.07
    ாம
    -0.07
    느
    -0.07
    POSITIVE LOGITS
    747
    0.08
    temps
    0.08
    Leap
    0.08
     Darwin
    0.07
    aping
    0.07
    ulating
    0.07
     leap
    0.07
    тация
    0.07
     תק
    0.07
     toen
    0.07
    Activations Density 0.001%

    No Known Activations