© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 529
    Prev
    Next
    INDEX
    Explanations

    Nelson Mandela

    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
     lädt
    -0.08
     مباشر
    -0.08
     evitando
    -0.08
     ambul
    -0.07
     zij
    -0.07
     Prec
    -0.07
     Datum
    -0.07
    ध्य
    -0.07
     precise
    -0.07
     evita
    -0.07
    POSITIVE LOGITS
    pine
    0.08
    :max
    0.08
    -max
    0.07
    -debug
    0.07
    gid
    0.07
     pedag
    0.07
     essence
    0.07
     grow
    0.07
    -re
    0.07
     qw
    0.07
    Activations Density 0.001%

    No Known Activations