© 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. 54735
    Prev
    Next
    INDEX
    Explanations

    drawing parameters

    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
    /Application
    -0.07
     hin
    -0.07
     Barcel
    -0.07
     пров
    -0.07
     múlt
    -0.07
     Noon
    -0.07
    arrera
    -0.07
     �
    -0.07
     hurd
    -0.07
    -0.07
    POSITIVE LOGITS
    очник
    0.09
     slit
    0.08
     shading
    0.08
    edance
    0.08
     ചിത്ര
    0.08
    наче
    0.08
     contam
    0.08
     oči
    0.08
     تصاویر
    0.08
     функцию
    0.08
    Activations Density 0.010%
    No Known Activations