© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21309
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    七码
    -0.11
    ♀♀♀♀♀♀
    -0.11
    发彩票
    -0.11
    六码
    -0.11
    铁算盘
    -0.11
    平刷
    -0.11
    _久久
    -0.10
    ,久久
    -0.10
    人人看
    -0.10
    直营网
    -0.10
    POSITIVE LOGITS
     entiendo
    0.14
     seems
    0.13
     tradução
    0.12
     descrição
    0.12
     sorry
    0.12
     context
    0.12
     description
    0.12
     screenshot
    0.11
    Seems
    0.11
     solicitado
    0.11
    Activations Density 0.245%

    No Known Activations