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. 44128
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    .inc
    -0.08
    त्व
    -0.08
    501
    -0.07
    .xt
    -0.07
    BAB
    -0.07
     എന്നീ
    -0.07
    asion
    -0.07
    صرف
    -0.07
    ulo
    -0.07
    (?)
    -0.07
    POSITIVE LOGITS
     corrupt
    0.07
    ensan
    0.07
     fla
    0.07
     сообщ
    0.07
     stwor
    0.07
     답
    0.07
     પુ
    0.07
     passat
    0.07
    .vstack
    0.07
    สนาม
    0.07
    Activations Density 0.003%

    No Known Activations