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. 60596
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    Anybody
    -0.09
    =h
    -0.09
    .ck
    -0.08
     قاعدة
    -0.08
    quet
    -0.08
    .cor
    -0.08
    Pedro
    -0.08
    _white
    -0.08
    _neighbor
    -0.08
    Corn
    -0.07
    POSITIVE LOGITS
     Map
    0.08
     location
    0.08
     BCE
    0.07
     developer
    0.07
     émotion
    0.07
     Person
    0.07
     emoções
    0.07
     emoties
    0.07
     emot
    0.07
     Micro
    0.07
    Activations Density 0.004%

    No Known Activations