© 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. 20398
    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
     国产精品
    -0.11
    _在线
    -0.11
     无码
    -0.11
     七喜
    -0.10
     
↵↵
    -0.10
     própr
    -0.10
     新宝
    -0.10
     ／
    -0.10
    ուսի
    -0.10
     中国福利彩票
    -0.10
    POSITIVE LOGITS
     that
    0.26
    that
    0.25
     bahwa
    0.23
    That
    0.23
     kwamba
    0.23
    	that
    0.23
     rằng
    0.22
     That
    0.20
     ότι
    0.20
     bahawa
    0.20
    Activations Density 0.058%

    No Known Activations