© 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. 64945
    Prev
    Next
    INDEX
    Explanations

    dash

    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
     Baja
    -0.07
     attitudes
    -0.07
     получать
    -0.07
     quantities
    -0.07
    Ble
    -0.07
     छ
    -0.07
     bottoms
    -0.07
    _DOCUMENT
    -0.07
     Дав
    -0.07
     विच
    -0.07
    POSITIVE LOGITS
     идет
    0.09
     uranium
    0.08
     wiederum
    0.08
     пройдет
    0.07
    jör
    0.07
     perc
    0.07
     mər
    0.07
    িড
    0.07
    Needs
    0.07
     단계
    0.07
    Activations Density 0.015%

    No Known Activations