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. 88129
    Prev
    Next
    INDEX
    Explanations

    winner

    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
     insured
    -0.08
     corporate
    -0.08
     commercial
    -0.08
    {"
    -0.07
     đề
    -0.07
    dagangan
    -0.07
     outdated
    -0.07
     phrases
    -0.07
    fall
    -0.07
     مح
    -0.07
    POSITIVE LOGITS
     levantar
    0.09
     acelerar
    0.08
     нат
    0.08
     oer
    0.08
     Transit
    0.08
     насы
    0.08
     acqu
    0.08
     отсутств
    0.07
    ريد
    0.07
    ска
    0.07
    Activations Density 0.003%

    No Known Activations