© 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. 48992
    Prev
    Next
    INDEX
    Explanations

    ugs

    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
     elected
    -0.10
    avedad
    -0.09
     রাষ্ট্র
    -0.09
    рых
    -0.09
     probation
    -0.09
     gouver
    -0.09
    制度
    -0.09
     heg
    -0.09
    unicip
    -0.08
     kilometer
    -0.08
    POSITIVE LOGITS
     mugs
    0.26
     Prints
    0.21
     Artwork
    0.21
    Artwork
    0.21
     artwork
    0.20
     Shirts
    0.20
     shirts
    0.20
     paintings
    0.19
     Etsy
    0.19
     Printable
    0.19
    Activations Density 0.030%

    No Known Activations