© 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. 929
    Prev
    Next
    INDEX
    Explanations

    math

    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
     lanes
    -0.10
     lane
    -0.09
     overnight
    -0.08
     rewind
    -0.08
    lane
    -0.08
    ("~/
    -0.08
     autoplay
    -0.08
     swipe
    -0.08
    edad
    -0.08
    amatta
    -0.08
    POSITIVE LOGITS
     spherical
    0.12
     tess
    0.12
     tetra
    0.11
    icos
    0.11
    _cube
    0.10
     celestial
    0.10
    _geometry
    0.10
     spheres
    0.10
     cube
    0.10
     sphere
    0.10
    Activations Density 0.020%

    No Known Activations