© 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. 114178
    Prev
    Next
    INDEX
    Explanations

    fragmented text

    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
    OD
    -0.08
     Eti
    -0.08
    Mgr
    -0.07
     Clause
    -0.07
    net
    -0.07
     OD
    -0.07
    偶
    -0.07
    enm
    -0.07
    DU
    -0.07
     Must
    -0.07
    POSITIVE LOGITS
    ̆
    0.09
     गये
    0.09
    ೕ
    0.09
     बढ
    0.09
     벌
    0.08
     whilst
    0.08
     बढ़
    0.08
    ýs
    0.08
    ̀
    0.08
    Dots
    0.07
    Activations Density 2.578%

    No Known Activations