© 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. 108590
    Prev
    Next
    INDEX
    Explanations

    forms

    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
     Democracy
    -0.09
    টা
    -0.08
     daughters
    -0.08
     Clinics
    -0.08
    ACCESS
    -0.08
    더
    -0.08
     docket
    -0.07
    user
    -0.07
     autonomie
    -0.07
     Chamber
    -0.07
    POSITIVE LOGITS
     medier
    0.08
    เพลง
    0.08
     ಸಾಹಿತ್ಯ
    0.08
     mediums
    0.08
    ото
    0.08
     spont
    0.08
     」
    0.08
     â
    0.08
     литера
    0.08
     há
    0.07
    Activations Density 0.005%

    No Known Activations