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. 15-RESID-POST-AA
    6. 19151
    Prev
    Next
    INDEX
    Explanations

    raw

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -info
    -0.08
     பற்ற
    -0.08
    val
    -0.07
    -setting
    -0.07
     emissão
    -0.07
    -main
    -0.07
    -information
    -0.07
     nghỉ
    -0.07
    -th
    -0.07
    -distance
    -0.07
    POSITIVE LOGITS
    มา
    0.10
     받은
    0.09
     raw
    0.09
    (raw
    0.09
    받
    0.08
     bruto
    0.08
     crappy
    0.08
    来的
    0.08
    /download
    0.08
     possession
    0.08
    Activations Density 0.037%

    No Known Activations