© 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. 11-RESID-POST-AA
    11. 31265
    Prev
    Next
    INDEX
    Explanations

    item/user content attributes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     upr
    -0.08
     nowrap
    -0.08
     mav
    -0.08
     perpet
    -0.07
     intermitt
    -0.07
     Nav
    -0.07
     Rene
    -0.07
     magni
    -0.07
     amid
    -0.07
     JV
    -0.07
    POSITIVE LOGITS
    _traits
    0.10
    traits
    0.10
    属性
    0.10
     attractiveness
    0.09
     allergens
    0.09
     popularity
    0.09
     traits
    0.09
    associate
    0.09
    ufacturer
    0.08
     Traits
    0.08
    Activations Density 0.015%

    No Known Activations