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. 53815
    Prev
    Next
    INDEX
    Explanations

    contrasting ideas

    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
    至
    -0.09
    指数
    -0.08
     Accent
    -0.08
    ります
    -0.08
    女士
    -0.08
    AIza
    -0.07
    厨
    -0.07
    stoffe
    -0.07
     Ladies
    -0.07
    -Val
    -0.07
    POSITIVE LOGITS
     sophisticated
    0.09
     technically
    0.08
    736
    0.08
     prolific
    0.08
     سه
    0.08
    923
    0.08
    636
    0.07
     historical
    0.07
     ✅
    0.07
     overt
    0.07
    Activations Density 0.050%

    No Known Activations