© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 96184
    Prev
    Next
    INDEX
    Explanations

    there

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Could
    -0.13
    Could
    -0.12
     könnte
    -0.10
    could
    -0.10
     Only
    -0.09
     pourrait
    -0.09
     Possibly
    -0.09
    Potential
    -0.09
     forskjellige
    -0.09
     pourraient
    -0.09
    POSITIVE LOGITS
     necessarily
    0.12
     inevitably
    0.11
     necesariamente
    0.10
     monoch
    0.10
     necessariamente
    0.10
     exhibited
    0.10
     encontrarás
    0.10
     inevitable
    0.09
    必
    0.09
     encontrará
    0.09
    Activations Density 0.030%

    No Known Activations