© 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 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. 63322
    Prev
    Next
    INDEX
    Explanations

    box

    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
     exces
    -0.08
    liche
    -0.08
    mäß
    -0.07
     Matteo
    -0.07
     Nicolas
    -0.07
     cong
    -0.07
     первым
    -0.07
     lich
    -0.07
    .sent
    -0.07
     moss
    -0.07
    POSITIVE LOGITS
     tegelijk
    0.13
     hinweg
    0.12
    、多
    0.11
     подряд
    0.09
    -ranging
    0.09
    対応
    0.08
     (>
    0.08
     heen
    0.08
    යක්
    0.08
     affair
    0.08
    Activations Density 0.057%

    No Known Activations