© 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. 47246
    Prev
    Next
    INDEX
    Explanations

    piece

    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
     weren
    -0.08
     yanında
    -0.08
    링
    -0.08
    、安全
    -0.08
     AVI
    -0.08
     spokeswoman
    -0.07
     specifics
    -0.07
     والمس
    -0.07
     zudem
    -0.07
     Texans
    -0.07
    POSITIVE LOGITS
     croche
    0.08
     реп
    0.07
    Snippet
    0.07
    Ï
    0.07
     Unterhaltung
    0.07
     Sass
    0.07
     Laurent
    0.07
    /fr
    0.07
     ই
    0.07
     участок
    0.07
    Activations Density 0.002%

    No Known Activations