© 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. 19-RESID-POST-AA
    11. 103353
    Prev
    Next
    INDEX
    Explanations

    Different languages "model"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    战略
    -0.09
     NATO
    -0.09
     drilled
    -0.08
    breadcrumb
    -0.08
    insured
    -0.08
    ASHINGTON
    -0.08
     declaration
    -0.08
     kế
    -0.08
     Canadians
    -0.08
    เทศ
    -0.08
    POSITIVE LOGITS
    模型
    0.17
    モデル
    0.16
     모델
    0.15
    _models
    0.15
     Models
    0.15
     models
    0.15
     моделей
    0.15
    .models
    0.14
     modèles
    0.14
     modelos
    0.14
    Activations Density 0.026%

    No Known Activations