© 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. 21209
    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
    传真
    -0.10
     OSHA
    -0.09
    wijk
    -0.08
     대통령
    -0.08
    书记
    -0.08
     감독
    -0.08
    blatt
    -0.08
    姚
    -0.08
    口诀
    -0.08
     quadrant
    -0.08
    POSITIVE LOGITS
    充值
    0.17
     Patreon
    0.17
     monet
    0.17
     satın
    0.17
     monetize
    0.16
     വാങ്ങ
    0.16
     purchases
    0.16
    金币
    0.16
     perks
    0.15
    premium
    0.15
    Activations Density 0.018%

    No Known Activations