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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 71368
    Prev
    Next
    INDEX
    Explanations

    arXiv/URLs

    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
     conductor
    -0.08
     alerts
    -0.07
    رص
    -0.07
    eddy
    -0.07
     Tochter
    -0.07
     Danger
    -0.07
     Sullivan
    -0.07
    urier
    -0.07
     ترا
    -0.07
     parcel
    -0.07
    POSITIVE LOGITS
    .Device
    0.09
    .kr
    0.09
    关于
    0.08
     uploaded
    0.08
    .cn
    0.08
    ://
    0.08
    .keras
    0.08
    `.↵
    0.08
    :///
    0.08
     äm
    0.08
    Activations Density 0.001%

    No Known Activations