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. 53824
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     expansion
    -0.08
    Cols
    -0.08
     permet
    -0.07
     restoration
    -0.07
     teb
    -0.07
     import
    -0.07
     large
    -0.07
     expand
    -0.07
     expansions
    -0.07
    .safe
    -0.07
    POSITIVE LOGITS
    bliche
    0.09
     სახ
    0.08
     воп
    0.08
     وسائل
    0.08
     Warsaw
    0.08
    �
    0.08
     QAction
    0.08
    chini
    0.08
    داء
    0.08
    来了
    0.08
    Activations Density 0.003%

    No Known Activations