© 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. 23-RESID-POST-AA
    11. 48147
    Prev
    Next
    INDEX
    Explanations

    PE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (contract
    -0.09
    .contract
    -0.09
    exec
    -0.09
     Carol
    -0.08
    .exec
    -0.08
    -contract
    -0.08
    Carol
    -0.08
    ogbu
    -0.08
     Оз
    -0.08
    contract
    -0.08
    POSITIVE LOGITS
     Integrity
    0.10
     PA
    0.09
     curses
    0.09
    _PA
    0.09
     Pro
    0.09
     integrity
    0.08
    PA
    0.08
     Web
    0.08
    ipay
    0.07
     DL
    0.07
    Activations Density 0.001%

    No Known Activations