© 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. 91273
    Prev
    Next
    INDEX
    Explanations

    leadership

    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
    chants
    -0.08
     Kub
    -0.08
     collider
    -0.07
     postage
    -0.07
     Kirst
    -0.07
     nond
    -0.07
    .at
    -0.07
    lag
    -0.07
    ところ
    -0.07
     Hass
    -0.07
    POSITIVE LOGITS
    십
    0.09
    🏼
    0.08
    skrä
    0.08
     leadership
    0.08
    🏻
    0.08
    감
    0.08
     Supremo
    0.08
    volle
    0.08
    领导
    0.08
     naval
    0.08
    Activations Density 0.022%

    No Known Activations