© 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. 25078
    Prev
    Next
    INDEX
    Explanations

    finance

    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
     camera
    -0.09
    TERY
    -0.08
     jaz
    -0.08
    NER
    -0.08
     ron
    -0.08
     oph
    -0.08
     Camera
    -0.07
    mera
    -0.07
    过程
    -0.07
    areness
    -0.07
    POSITIVE LOGITS
     الاجتماعية
    0.08
    কল
    0.08
    [var
    0.08
    .total
    0.08
    -solving
    0.07
    .margin
    0.07
    х
    0.07
     ว
    0.07
    .flatten
    0.07
     список
    0.07
    Activations Density 0.001%

    No Known Activations