© 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. 3-RESID-POST-AA
    11. 12837
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     μέ
    -0.08
     Rat
    -0.08
     Mayo
    -0.08
     Palais
    -0.07
    ‌ی
    -0.07
     Kurt
    -0.07
     εμπ
    -0.07
     ανά
    -0.07
     ν
    -0.07
     Fut
    -0.07
    POSITIVE LOGITS
     rotary
    0.09
    Overs
    0.08
     attacking
    0.07
     hon
    0.07
    (format
    0.07
     отправ
    0.07
    =format
    0.07
    otes
    0.07
     overs
    0.07
    _exec
    0.07
    Activations Density 0.010%

    No Known Activations