© 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. 96331
    Prev
    Next
    INDEX
    Explanations

    ʻ

    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
    itus
    -0.09
     UTIL
    -0.08
     prisons
    -0.08
     Herald
    -0.08
     Newspaper
    -0.08
     Security
    -0.08
     Sicherheits
    -0.08
     개최
    -0.08
     sher
    -0.08
     Lancaster
    -0.07
    POSITIVE LOGITS
     anima
    0.09
    anime
    0.08
     write
    0.08
    anim
    0.08
    Anim
    0.08
    fang
    0.08
    where
    0.08
    lumbr
    0.08
    τα
    0.07
     where
    0.07
    Activations Density 0.000%

    No Known Activations