© 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. 54835
    Prev
    Next
    INDEX
    Explanations

    occupational

    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
     accurately
    -0.09
    ル
    -0.07
     verses
    -0.07
     divisor
    -0.07
     alert
    -0.07
     line
    -0.07
     verse
    -0.07
    _ib
    -0.07
    48
    -0.07
     viva
    -0.07
    POSITIVE LOGITS
     Clock
    0.10
    clock
    0.10
    .clock
    0.09
    商城
    0.09
    ショップ
    0.09
    Clock
    0.09
    -clock
    0.09
     Therapy
    0.08
    (JSON
    0.08
    Workshop
    0.08
    Activations Density 0.003%

    No Known Activations