© 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. 113176
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
     Ian
    -0.09
    인다
    -0.08
     envolver
    -0.08
    Ian
    -0.08
     अन्तर
    -0.07
    UNA
    -0.07
     Isl
    -0.07
    ён
    -0.07
     konstruk
    -0.07
     enkele
    -0.07
    POSITIVE LOGITS
    zano
    0.08
    بيعات
    0.08
     Collabor
    0.07
    _products
    0.07
    ضايا
    0.07
    زز
    0.07
    odable
    0.07
    ظهر
    0.07
    باط
    0.07
    زند
    0.07
    Activations Density 0.001%

    No Known Activations