© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 95649
    Prev
    Next
    INDEX
    Explanations

    spice recipes

    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
     UIGraphics
    -0.09
    archives
    -0.08
    _adapter
    -0.08
    /browser
    -0.08
     algun
    -0.08
     Verbrauch
    -0.08
    /assets
    -0.08
    luss
    -0.07
    /screens
    -0.07
     vyr
    -0.07
    POSITIVE LOGITS
     oregano
    0.12
     cumin
    0.12
     seasoning
    0.11
     garlic
    0.09
     spices
    0.09
     thyme
    0.09
     turmeric
    0.09
     salt
    0.09
     mustard
    0.08
    Salt
    0.08
    Activations Density 0.050%

    No Known Activations