© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 68398
    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
    <Array
    -0.08
     Leeds
    -0.08
     발견
    -0.08
     opged
    -0.08
    나요
    -0.07
     ظهر
    -0.07
     Denise
    -0.07
    :Array
    -0.07
    ตรง
    -0.07
     Metropolitana
    -0.07
    POSITIVE LOGITS
    几十
    0.13
    Typically
    0.12
     Обычно
    0.12
    typically
    0.12
    例えば
    0.11
     esimerkiksi
    0.11
     typically
    0.11
    ，例如
    0.11
     Например
    0.11
    通常
    0.10
    Activations Density 0.057%

    No Known Activations