© 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. 54544
    Prev
    Next
    INDEX
    Explanations

    gelatin

    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
     winger
    -0.08
     lob
    -0.08
     đất
    -0.08
    -born
    -0.08
    ciąż
    -0.08
     Admir
    -0.08
     artery
    -0.08
    داری
    -0.08
    lád
    -0.08
     favors
    -0.07
    POSITIVE LOGITS
     gelatin
    0.10
     punkt
    0.08
    unicode
    0.07
     Low
    0.07
     Genuss
    0.07
     spooky
    0.07
    (gr
    0.07
     rele
    0.07
    Unicode
    0.07
     medical
    0.07
    Activations Density 0.003%

    No Known Activations