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. 77306
    Prev
    Next
    INDEX
    Explanations

    software configuration/code

    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
     Lancaster
    -0.09
    รอง
    -0.09
     diversion
    -0.08
    utting
    -0.08
     defender
    -0.08
     projected
    -0.08
    áló
    -0.08
     sucedido
    -0.08
     RHS
    -0.08
     foret
    -0.07
    POSITIVE LOGITS
    目录
    0.11
    /)
    0.10
     ഡയറ
    0.10
    _folder
    0.10
    Folder
    0.10
     folder
    0.10
    /**/*
    0.09
    /*.
    0.09
     Folder
    0.09
    /{
    0.09
    Activations Density 0.031%

    No Known Activations