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. 77376
    Prev
    Next
    INDEX
    Explanations

    Code fragments

    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
     Cox
    -0.08
    ,-
    -0.07
     સરળ
    -0.07
     embassy
    -0.07
    检
    -0.07
     Messer
    -0.07
    Inspector
    -0.07
    Mot
    -0.07
    .emb
    -0.07
    Getter
    -0.07
    POSITIVE LOGITS
     yli
    0.09
    째
    0.09
     lastly
    0.09
     домой
    0.08
     назад
    0.08
     Lastly
    0.08
     Twelve
    0.08
     multicultural
    0.08
     hjæl
    0.08
     마
    0.08
    Activations Density 0.067%

    No Known Activations