© 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. 7578
    Prev
    Next
    INDEX
    Explanations

    survey

    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
     immin
    -0.09
     pristine
    -0.08
    uc
    -0.07
     unsupported
    -0.07
     tempus
    -0.07
    crypto
    -0.07
    ప్ట
    -0.07
    中文
    -0.07
     writable
    -0.07
     mits
    -0.07
    POSITIVE LOGITS
    调查
    0.12
     조사
    0.11
     실시
    0.11
    统计
    0.11
     Histogram
    0.10
     menée
    0.10
     നടത്തിയ
    0.10
     conducted
    0.09
     Statistik
    0.09
     estadísticas
    0.09
    Activations Density 0.028%

    No Known Activations