© 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. 899
    Prev
    Next
    INDEX
    Explanations

    2

    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
     relic
    -0.08
     beaut
    -0.08
    fac
    -0.08
     Pony
    -0.07
     pony
    -0.07
     bearer
    -0.07
     richiesta
    -0.07
     skull
    -0.07
     glitter
    -0.07
    skin
    -0.07
    POSITIVE LOGITS
     réput
    0.08
    ിയ
    0.08
    στό
    0.08
    -gh
    0.07
    ూ
    0.07
    ніх
    0.07
    SCI
    0.07
     Steen
    0.07
     Gh
    0.07
    分别
    0.07
    Activations Density 0.093%

    No Known Activations