© 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. 70725
    Prev
    Next
    INDEX
    Explanations

    当

    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
     intense
    -0.08
     cushion
    -0.08
     desl
    -0.08
     encontr
    -0.08
     settle
    -0.08
     vel
    -0.07
     Ashe
    -0.07
     dwind
    -0.07
     bla
    -0.07
     tenho
    -0.07
    POSITIVE LOGITS
    ناً
    0.08
    ence
    0.07
    อย่าง
    0.07
     ચોક
    0.07
    哥
    0.07
     السين
    0.07
    elseif
    0.07
     איש
    0.07
    כ
    0.07
     fiind
    0.07
    Activations Density 0.004%

    No Known Activations