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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70796
    Prev
    Next
    INDEX
    Explanations

    present tense

    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
    죽
    -0.08
    <|reserved_200011|>
    -0.08
    (display
    -0.08
     waste
    -0.08
    τέρ
    -0.08
     exhibit
    -0.08
    _scal
    -0.07
    Waste
    -0.07
    ціон
    -0.07
    _targets
    -0.07
    POSITIVE LOGITS
     nonfiction
    0.08
     Fresh
    0.08
     frisch
    0.08
     fresh
    0.08
     jon
    0.08
     vibe
    0.08
     Journey
    0.08
     pudding
    0.08
    fresh
    0.08
    Fresh
    0.08
    Activations Density 0.001%

    No Known Activations