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. 30675
    Prev
    Next
    INDEX
    Explanations

    biscotti

    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
    obox
    -0.08
    
    ↵
    -0.07
     સૌથી
    -0.07
    438
    -0.07
    Summ
    -0.07
    au
    -0.07
    目前
    -0.07
    grunn
    -0.07
    ылы
    -0.07
    chner
    -0.07
    POSITIVE LOGITS
    สู
    0.09
    ദ്ദ
    0.09
     vitam
    0.08
     दु
    0.08
     preparo
    0.08
    ഞ്ജ
    0.08
     आद
    0.08
    iedenis
    0.08
     काट
    0.08
     spezi
    0.08
    Activations Density 0.001%

    No Known Activations