© 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. 99853
    Prev
    Next
    INDEX
    Explanations

    1

    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
    ัน
    -0.10
    ันว
    -0.09
     swords
    -0.09
     clap
    -0.08
     circulating
    -0.08
     drummer
    -0.08
    -haired
    -0.08
     condiv
    -0.07
    áns
    -0.07
     naval
    -0.07
    POSITIVE LOGITS
    ici
    0.08
     Impress
    0.08
    .આ
    0.07
     hearings
    0.07
    SPECIAL
    0.07
     સાં
    0.07
     ગ્રાહ
    0.07
     özel
    0.07
    Tou
    0.07
     પ્રસ
    0.07
    Activations Density 0.026%

    No Known Activations