© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31346
    Prev
    Next
    INDEX
    Explanations

    measurements and accuracy

    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
     Stanton
    -0.09
     задум
    -0.08
    -END
    -0.08
     visions
    -0.08
     Visibility
    -0.08
    @Configuration
    -0.08
     visiter
    -0.08
     initiatives
    -0.08
    IDDEN
    -0.08
    Visibility
    -0.08
    POSITIVE LOGITS
     kilograms
    0.18
     kilogram
    0.17
    重量
    0.17
    公斤
    0.16
     grams
    0.14
     weight
    0.14
     वजन
    0.14
     وزن
    0.13
    _weight
    0.13
    (weight
    0.13
    Activations Density 0.067%

    No Known Activations