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

    Neuronpedia

    APICircuit 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. 75965
    Prev
    Next
    INDEX
    Explanations

    AI

    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
    EMPL
    -0.08
    OUNDS
    -0.07
     América
    -0.07
    España
    -0.07
     Tigers
    -0.07
    prit
    -0.07
    Mar
    -0.07
    itting
    -0.07
    Michigan
    -0.07
    ités
    -0.07
    POSITIVE LOGITS
    .lines
    0.08
     மூலம்
    0.08
    /svg
    0.08
     হিসেবে
    0.08
     tersebut
    0.08
     shell
    0.08
     হিসাবে
    0.07
     арқылы
    0.07
     orqali
    0.07
     пока
    0.07
    Activations Density 0.003%

    No Known Activations