© 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. 25263
    Prev
    Next
    INDEX
    Explanations

    Code and/or math computations

    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
     Yum
    -0.08
     Ho
    -0.07
     Uno
    -0.07
     OD
    -0.07
     Ci
    -0.07
    Ho
    -0.07
    alami
    -0.07
     maka
    -0.07
     Eti
    -0.07
     thumbs
    -0.07
    POSITIVE LOGITS
    jub
    0.08
    een
    0.08
    bul
    0.08
     sr
    0.08
     Sacramento
    0.08
    ăng
    0.07
    Unt
    0.07
    /she
    0.07
     Huang
    0.07
    mdash
    0.07
    Activations Density 0.415%

    No Known Activations