© 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. 114153
    Prev
    Next
    INDEX
    Explanations

    Instructions and coarse textures

    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
     బ్య
    -0.10
     infrastrukt
    -0.08
    DH
    -0.08
     sava
    -0.08
    -million
    -0.07
     footprint
    -0.07
    IMAL
    -0.07
    .bootstrap
    -0.07
     viz
    -0.07
    财政
    -0.07
    POSITIVE LOGITS
    HTTPRequest
    0.08
    aughty
    0.08
    яя
    0.08
    urray
    0.08
     Constraints
    0.07
     ไป
    0.07
    _similarity
    0.07
    _plain
    0.07
     markdown
    0.07
    eree
    0.07
    Activations Density 0.003%

    No Known Activations