© 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. 22493
    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
     lately
    -0.08
     없는
    -0.08
    +
    -0.08
     and
    -0.08
     destroyed
    -0.08
    armed
    -0.07
    if
    -0.07
     tailored
    -0.07
     deleted
    -0.07
     và
    -0.07
    POSITIVE LOGITS
     означает
    0.21
     means
    0.20
     betekent
    0.20
     يعني
    0.19
     tähendab
    0.19
    意味着
    0.19
     bedeutet
    0.19
     innebär
    0.18
     मतलब
    0.18
     significa
    0.18
    Activations Density 0.071%

    No Known Activations