© 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. 19864
    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
    andum
    -0.10
    〒
    -0.08
     hairstyles
    -0.08
    极品
    -0.08
     chipset
    -0.07
     industriais
    -0.07
     Haar
    -0.07
     dataframe
    -0.07
    928
    -0.07
     yuq
    -0.07
    POSITIVE LOGITS
     seconds
    0.33
    Seconds
    0.33
    _seconds
    0.32
    (seconds
    0.30
    seconds
    0.30
    .seconds
    0.29
    _SECONDS
    0.28
     Sekunden
    0.28
     Seconds
    0.27
    秒
    0.27
    Activations Density 0.005%

    No Known Activations