© 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. 113174
    Prev
    Next
    INDEX
    Explanations

    Titles and descriptions

    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
    ிப
    -0.08
    这么
    -0.08
    wid
    -0.07
    -0.07
     buts
    -0.07
    ı
    -0.07
     ofere
    -0.07
    Hyper
    -0.07
    主体
    -0.07
     useless
    -0.07
    POSITIVE LOGITS
     ши
    0.08
     גר
    0.08
     겨
    0.08
    astr
    0.07
    inrin
    0.07
     എന്നിവർ
    0.07
     וצ
    0.07
    ‍ഹ
    0.07
     పుర
    0.07
    .seg
    0.07
    Activations Density 0.041%
    No Known Activations