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. 43990
    Prev
    Next
    INDEX
    Explanations

    Battlefield scenes

    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
    Minimum
    -0.08
    Accommodation
    -0.08
     annuelle
    -0.08
     માંગ
    -0.08
    ને
    -0.08
    Directories
    -0.07
     accommod
    -0.07
    -flex
    -0.07
     commitment
    -0.07
     צר
    -0.07
    POSITIVE LOGITS
     pertenc
    0.09
    راقي
    0.08
     পো
    0.08
     সৈ
    0.08
    战
    0.08
    moo
    0.08
     update
    0.08
     Bally
    0.08
    .def
    0.08
    .dp
    0.08
    Activations Density 0.005%

    No Known Activations