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. 88186
    Prev
    Next
    INDEX
    Explanations

    emic

    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
    േക്ഷ
    -0.08
     Milwaukee
    -0.08
    (dev
    -0.08
    're
    -0.08
    _dev
    -0.07
    રિક
    -0.07
    Serv
    -0.07
     Vere
    -0.07
    лова
    -0.07
     sekä
    -0.07
    POSITIVE LOGITS
     Poverty
    0.07
     ru
    0.07
     Whitening
    0.07
     Zam
    0.07
    ania
    0.07
    Nao
    0.07
    」は
    0.07
     contractual
    0.07
     Weld
    0.07
     Wings
    0.07
    Activations Density 0.253%

    No Known Activations