© 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. 11-RESID-POST-AA
    6. 75814
    Prev
    Next
    INDEX
    Explanations

    instructions and limitations

    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
     ours
    -0.07
    ,\"
    -0.07
     Belg
    -0.07
    อกจาก
    -0.07
    ASH
    -0.07
    orset
    -0.07
    дағы
    -0.07
     Gef
    -0.07
    焦
    -0.07
    χος
    -0.07
    POSITIVE LOGITS
    send
    0.08
    /tools
    0.08
    /tool
    0.08
     conocimiento
    0.07
     communicating
    0.07
     comunicaciones
    0.07
    acyo
    0.07
     conhecimentos
    0.07
     conocimientos
    0.07
     المعرفة
    0.07
    Activations Density 0.001%

    No Known Activations