© 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. 45448
    Prev
    Next
    INDEX
    Explanations

    glycerin or acid

    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
     ske
    -0.08
     numeric
    -0.08
     mold
    -0.08
     Apost
    -0.08
    াজ
    -0.08
     Zool
    -0.08
     endocr
    -0.07
     mí
    -0.07
     numerical
    -0.07
     competitive
    -0.07
    POSITIVE LOGITS
     champagne
    0.10
     refreshing
    0.09
     помогает
    0.09
     минуты
    0.09
    Ⅰ
    0.09
    �t
    0.08
    umbani
    0.08
    illos
    0.08
    ülen
    0.08
    orges
    0.08
    Activations Density 0.001%

    No Known Activations