© 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. 77989
    Prev
    Next
    INDEX
    Explanations

    formatting/emphasis

    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
    子的
    -0.08
     극
    -0.08
     advertised
    -0.08
     નહિ
    -0.08
    ieres
    -0.08
    _given
    -0.08
     아니라
    -0.07
     नहीं
    -0.07
    ไม่
    -0.07
    (IR
    -0.07
    POSITIVE LOGITS
     bri
    0.11
     esimerkiksi
    0.10
     puntual
    0.08
    ucose
    0.08
    lah
    0.08
    've
    0.08
     progrès
    0.07
    ої
    0.07
     River
    0.07
    <head
    0.07
    Activations Density 0.049%

    No Known Activations