© 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. 15-RESID-POST-AA
    11. 16459
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دقیق
    -0.08
     מתוך
    -0.08
    итать
    -0.08
     behaviours
    -0.08
     savour
    -0.08
     imati
    -0.08
    histor
    -0.08
     gratitude
    -0.08
    оват
    -0.08
     وزن
    -0.08
    POSITIVE LOGITS
     Sierra
    0.09
     Smith
    0.08
     Fresno
    0.08
     Arizona
    0.08
     Sioux
    0.08
     Illinois
    0.08
     Constitution
    0.08
     Santa
    0.08
     defendant
    0.07
     Secretary
    0.07
    Activations Density 0.002%

    No Known Activations