© 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. 78771
    Prev
    Next
    INDEX
    Explanations

    Rich library/logging

    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
     Bezug
    -0.08
     avi
    -0.08
    211
    -0.08
    -0.07
    Playable
    -0.07
     flight
    -0.07
    (lat
    -0.07
     крат
    -0.07
    202
    -0.07
     MVC
    -0.07
    POSITIVE LOGITS
     UIGraphics
    0.09
     برا
    0.08
     الوس
    0.08
     atop
    0.08
     šir
    0.08
     সুখ
    0.08
     siapa
    0.08
     mesurer
    0.08
     zusätzlichen
    0.08
     إش
    0.08
    Activations Density 0.000%
    No Known Activations