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. 53157
    Prev
    Next
    INDEX
    Explanations

    imuth

    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
    .modules
    -0.08
    [x
    -0.08
     Naked
    -0.08
    [module
    -0.07
     seemingly
    -0.07
    [index
    -0.07
    FLAG
    -0.07
     sov
    -0.07
    [contains
    -0.07
     seques
    -0.07
    POSITIVE LOGITS
    imuth
    0.09
     panoramic
    0.09
    pathname
    0.09
     Course
    0.08
    室
    0.08
     kasar
    0.07
     externo
    0.07
     CPL
    0.07
    terior
    0.07
     그대로
    0.07
    Activations Density 0.003%

    No Known Activations