© 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. 25975
    Prev
    Next
    INDEX
    Explanations

    obligation

    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
     burglary
    -0.09
     garşy
    -0.08
     growing
    -0.08
    mati
    -0.08
    .^
    -0.08
    Ն
    -0.08
     możliwo
    -0.08
     burgeoning
    -0.08
     grown
    -0.08
     Elisa
    -0.07
    POSITIVE LOGITS
     außerdem
    0.10
     кав
    0.09
     insgesamt
    0.09
     соблюдать
    0.09
     uppercase
    0.09
    _timezone
    0.08
     timezone
    0.08
     italic
    0.08
     Additional
    0.08
     inoltre
    0.08
    Activations Density 0.014%

    No Known Activations