© 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 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. 19990
    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
    ,免费
    -0.13
    -天天
    -0.13
    ,天天
    -0.12
     յուրաքանչյուր
    -0.12
    ларниң
    -0.12
    ләрниң
    -0.12
    ,欧美
    -0.12
     جيڪو
    -0.12
     թիմ
    -0.12
    ,亚洲
    -0.11
    POSITIVE LOGITS
     be
    0.22
    被
    0.21
     have
    0.21
     being
    0.19
    是
    0.19
     être
    0.18
     быть
    0.18
     been
    0.18
    有所
    0.17
    成为
    0.17
    Activations Density 0.050%

    No Known Activations