© 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. 71068
    Prev
    Next
    INDEX
    Explanations

    усп

    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
    贵
    -0.08
     ale
    -0.08
     sadd
    -0.08
     Herkunft
    -0.08
     Simmons
    -0.08
    .Username
    -0.08
    angements
    -0.08
    .Children
    -0.07
    ロン
    -0.07
     variance
    -0.07
    POSITIVE LOGITS
     갖
    0.08
    كنت
    0.08
    ّت
    0.08
    zeitig
    0.07
     मुस
    0.07
     ملي
    0.07
     plenty
    0.07
    Ps
    0.07
     consultar
    0.07
    niejs
    0.07
    Activations Density 0.008%

    No Known Activations