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. 11709
    Prev
    Next
    INDEX
    Explanations

    秋

    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
     Cef
    -0.08
    rosa
    -0.08
     Causes
    -0.08
     اللون
    -0.07
    'él
    -0.07
    osters
    -0.07
     inducing
    -0.07
    ‌ర
    -0.07
    wendig
    -0.07
    settings
    -0.07
    POSITIVE LOGITS
     muc
    0.08
     nect
    0.08
     stigma
    0.08
     specie
    0.07
     acompanh
    0.07
     자리
    0.07
    贤
    0.07
     mucus
    0.07
     valida
    0.07
    acky
    0.07
    Activations Density 0.003%

    No Known Activations