© 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. 22589
    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
     Thus
    -0.09
    于是
    -0.08
     ফলে
    -0.08
     võib
    -0.08
     haha
    -0.08
     yr
    -0.08
     rarely
    -0.08
     joten
    -0.08
     (
    -0.08
     त्यामुळे
    -0.08
    POSITIVE LOGITS
     구현
    0.18
    Implement
    0.15
     implement
    0.15
     Implement
    0.15
    实现
    0.15
     implementación
    0.14
     implemented
    0.14
     Implementation
    0.13
     implementar
    0.13
     implementation
    0.13
    Activations Density 0.053%

    No Known Activations