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. 53799
    Prev
    Next
    INDEX
    Explanations

    Business strategy/planning

    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
    iju
    -0.08
     Jin
    -0.07
    ior
    -0.07
    ikle
    -0.07
     Elf
    -0.07
     dobrze
    -0.07
     \↵
    -0.07
     numerous
    -0.07
    lec
    -0.07
     firstly
    -0.07
    POSITIVE LOGITS
     Specific
    0.09
     --------------------------------
    0.08
     ----------------------------------------------------------------
    0.08
    **↵↵
    0.08
    .general
    0.07
     /*#__
    0.07
     Explained
    0.07
     =================
    0.07
     =================================================================================
    0.07
     =================================================================
    0.07
    Activations Density 0.327%

    No Known Activations