Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 43927
    Prev
    Next
    INDEX
    Explanations

    disaster relief

    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
    -Br
    -0.08
     boundaries
    -0.08
    скую
    -0.08
     boundary
    -0.08
    κη
    -0.08
    дарды
    -0.08
    дардың
    -0.08
    יקות
    -0.07
     faisant
    -0.07
     pertinentes
    -0.07
    POSITIVE LOGITS
     desperately
    0.09
     mensen
    0.08
     people
    0.08
     dringend
    0.08
     isempty
    0.08
    焦
    0.08
     hearty
    0.08
    "It's
    0.07
     saliva
    0.07
     mattresses
    0.07
    Activations Density 0.038%

    No Known Activations