© 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. 95402
    Prev
    Next
    INDEX
    Explanations

    The word fancy

    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
     Yaz
    -0.08
     quente
    -0.07
    伸
    -0.07
     obrig
    -0.07
    .strict
    -0.07
    স্ব
    -0.07
     വര്
    -0.07
    Quiet
    -0.07
     estrem
    -0.07
    orrent
    -0.07
    POSITIVE LOGITS
     tricks
    0.10
     fancy
    0.09
     sophist
    0.09
     hơn
    0.08
     traps
    0.08
     kokoa
    0.08
    Fancy
    0.08
     enough
    0.08
    _ball
    0.08
     dances
    0.08
    Activations Density 0.012%

    No Known Activations