© 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. 19952
    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
    ]()↵
    -0.09
     偷拍
    -0.09
     //----------------
    -0.09
     高升
    -0.09
     满堂
    -0.09
    -0.09
    -0.09
    ំហំ
    -0.09
     狠狠
    -0.09
     бөтә
    -0.09
    POSITIVE LOGITS
    However
    0.13
     However
    0.13
    But
    0.12
     it's
    0.11
    B
    0.11
    ，需要
    0.11
    It's
    0.11
    Alternatively
    0.10
     jedoch
    0.10
    They
    0.10
    Activations Density 0.015%
    No Known Activations