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. 12182
    Prev
    Next
    INDEX
    Explanations

    lowest

    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
     Bolton
    -0.09
    ourcen
    -0.08
    orne
    -0.08
    /render
    -0.07
     lente
    -0.07
    梁
    -0.07
    -li
    -0.07
    mk
    -0.07
    ocab
    -0.07
    claimed
    -0.07
    POSITIVE LOGITS
    াব
    0.08
    Med
    0.08
    _CANCEL
    0.08
    _med
    0.08
     adsorption
    0.07
     demean
    0.07
    spolit
    0.07
    .Accept
    0.07
     Camps
    0.07
     എന്നിവ
    0.07
    Activations Density 0.014%

    No Known Activations