© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 838
    Prev
    Next
    INDEX
    Explanations

    Japanese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    생활
    -0.08
     જીવન
    -0.08
    кі
    -0.08
     জীবন
    -0.08
     abilities
    -0.08
    ogical
    -0.07
     biom
    -0.07
    but
    -0.07
    生活
    -0.07
     өмір
    -0.07
    POSITIVE LOGITS
     표시
    0.08
     زیادی
    0.08
     Toledo
    0.08
     бывают
    0.08
    ously
    0.08
     Cause
    0.08
     бывает
    0.08
     Trudeau
    0.07
    ადად
    0.07
     Lopez
    0.07
    Activations Density 0.003%

    No Known Activations