© 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. 31502
    Prev
    Next
    INDEX
    Explanations

    distance and position

    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
    ate
    -0.08
    573
    -0.07
     scissors
    -0.07
     ते
    -0.07
    eps
    -0.07
     Zust
    -0.06
     Genome
    -0.06
    .cp
    -0.06
    ştur
    -0.06
    {{
    -0.06
    POSITIVE LOGITS
    بلی
    0.09
     yönelik
    0.09
    方向
    0.09
     арналған
    0.08
     принадлеж
    0.08
    assat
    0.08
    étiques
    0.08
    wendungen
    0.08
     бағыт
    0.08
    (lang
    0.08
    Activations Density 0.018%

    No Known Activations