© 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. 78945
    Prev
    Next
    INDEX
    Explanations

    the

    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
    freeze
    -0.08
     Contributions
    -0.08
    (repo
    -0.08
     draining
    -0.08
    itening
    -0.07
     friendliness
    -0.07
    iterr
    -0.07
    -ID
    -0.07
    ;*/↵
    -0.07
     turnovers
    -0.07
    POSITIVE LOGITS
     jeden
    0.08
    原创
    0.08
    主题
    0.08
     imaginative
    0.08
    鬼
    0.08
     Kannada
    0.07
     adlı
    0.07
     burger
    0.07
     imaginary
    0.07
     kini
    0.07
    Activations Density 0.006%

    No Known Activations