© 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. 7621
    Prev
    Next
    INDEX
    Explanations

    Fate/kaleid Prisma Illya

    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
     engenharia
    -0.08
     concentrating
    -0.08
    .eval
    -0.08
     concentração
    -0.08
     tallest
    -0.08
     suction
    -0.08
    SEMB
    -0.07
    evas
    -0.07
     concentrate
    -0.07
    eval
    -0.07
    POSITIVE LOGITS
     объ
    0.08
     conf
    0.07
    clock
    0.07
    layout
    0.07
    0.07
     meios
    0.07
    sexual
    0.07
     komp
    0.07
    _CLOCK
    0.07
    office
    0.07
    Activations Density 0.002%
    No Known Activations