© 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. 20672
    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
    μεριν
    -0.08
     excerpts
    -0.08
     свої
    -0.07
     expressions
    -0.07
    <style
    -0.07
     sisse
    -0.07
     citations
    -0.07
     januar
    -0.07
     gelip
    -0.07
    ឡ
    -0.07
    POSITIVE LOGITS
    另一
    0.14
     opposite
    0.14
     farther
    0.13
     another
    0.13
     adjacent
    0.12
     بعيد
    0.12
     otro
    0.12
     sibling
    0.12
     completing
    0.12
     next
    0.12
    Activations Density 0.033%

    No Known Activations