Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11745
    Prev
    Next
    INDEX
    Explanations

    Conditionals/Choices

    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
    ตร
    -0.09
     exposures
    -0.08
     Exposure
    -0.08
     oit
    -0.08
     jing
    -0.07
    Exposure
    -0.07
    ्ट्र
    -0.07
    สูตร
    -0.07
    สี
    -0.07
     workings
    -0.07
    POSITIVE LOGITS
     willing
    0.14
    愿
    0.14
     willingness
    0.13
     willingly
    0.12
     enthous
    0.12
    願
    0.12
     freiwill
    0.12
     unwilling
    0.12
     consent
    0.11
     Bereits
    0.11
    Activations Density 0.109%

    No Known Activations