© 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. 75681
    Prev
    Next
    INDEX
    Explanations

    coordinates

    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
     jusqu
    -0.09
     Jusqu
    -0.09
     വിധ
    -0.08
    fois
    -0.08
    Until
    -0.08
     crayons
    -0.08
     modulo
    -0.08
     pesada
    -0.08
     ≥
    -0.07
     mutil
    -0.07
    POSITIVE LOGITS
     admin
    0.09
     Pune
    0.09
     Chinatown
    0.08
    _ADMIN
    0.08
     Admin
    0.08
     amenities
    0.08
     center
    0.08
    Admin
    0.08
     Patel
    0.08
     Zillow
    0.08
    Activations Density 0.002%

    No Known Activations