© 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. 95829
    Prev
    Next
    INDEX
    Explanations

    士

    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
    వ
    -0.09
    hav
    -0.08
     הנ
    -0.08
     האר
    -0.08
    aveni
    -0.08
     תמ
    -0.07
    స
    -0.07
    .errors
    -0.07
    ison
    -0.07
    ury
    -0.07
    POSITIVE LOGITS
     uff
    0.08
     Brokers
    0.08
     bò
    0.08
    achtet
    0.08
     scouts
    0.08
     Anal
    0.08
     Tok
    0.07
     rằng
    0.07
     Markets
    0.07
     astuces
    0.07
    Activations Density 0.003%

    No Known Activations