© 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. 21903
    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
     იხ
    -0.10
    江苏快
    -0.09
    五分彩
    -0.09
     福利彩票
    -0.09
    杀号
    -0.09
    分分彩
    -0.09
     易购
    -0.09
     体育彩票
    -0.09
    彩票官网
    -0.09
    _色
    -0.09
    POSITIVE LOGITS
     problem
    0.20
     Problem
    0.16
    問題
    0.16
     문제
    0.15
     समस्या
    0.15
     সমস্য
    0.15
    问题
    0.15
     Given
    0.15
    Given
    0.15
    Problem
    0.15
    Activations Density 0.041%

    No Known Activations