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. 55972
    Prev
    Next
    INDEX
    Explanations

    Russian language

    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
    alien
    -0.07
    रीन
    -0.07
    interactive
    -0.07
    IL
    -0.07
     geringer
    -0.07
     generous
    -0.07
    uffle
    -0.07
    (rec
    -0.07
    cust
    -0.07
    編
    -0.07
    POSITIVE LOGITS
     Tucker
    0.07
    াষ্ট্র
    0.07
     broom
    0.07
     Torrent
    0.07
     Государ
    0.07
     maman
    0.07
     obej
    0.07
    amaan
    0.07
    ocidad
    0.07
     velocity
    0.07
    Activations Density 0.003%

    No Known Activations