© 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. 70093
    Prev
    Next
    INDEX
    Explanations

    binary code

    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
    Loot
    -0.09
    Enchant
    -0.09
    Throwable
    -0.09
     offseason
    -0.08
    Sal
    -0.08
     throwable
    -0.08
    Sho
    -0.08
    Ali
    -0.08
     Loot
    -0.08
     entice
    -0.08
    POSITIVE LOGITS
     बिट
    0.15
     binary
    0.14
    (bits
    0.14
    .binary
    0.14
    _bits
    0.13
    _binary
    0.13
    .Binary
    0.13
    (binary
    0.13
     bits
    0.12
    binary
    0.12
    Activations Density 0.031%

    No Known Activations