© 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. 97339
    Prev
    Next
    INDEX
    Explanations

    face

    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
     shipments
    -0.08
     boats
    -0.08
     Rail
    -0.08
     bikes
    -0.08
     Boden
    -0.08
     newsletter
    -0.08
     Shipment
    -0.07
     freight
    -0.07
     newsletters
    -0.07
     trampoline
    -0.07
    POSITIVE LOGITS
     얼굴
    0.41
     facial
    0.40
     चेहरे
    0.39
    脸
    0.38
     rosto
    0.37
     face
    0.37
     faces
    0.36
     Facial
    0.35
     visage
    0.35
     ముఖ
    0.35
    Activations Density 0.140%

    No Known Activations