© 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 EvalsExportsAPI 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. 63630
    Prev
    Next
    INDEX
    Explanations

    horizontal line

    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
     Mér
    -0.08
    Predicate
    -0.08
     bạn
    -0.08
    roq
    -0.08
    ummi
    -0.08
    Sprite
    -0.07
    LOGIN
    -0.07
    Tim
    -0.07
    RSpec
    -0.07
    rush
    -0.07
    POSITIVE LOGITS
     sector
    0.08
     settore
    0.07
     따라서
    0.07
    നായ
    0.07
     nosa
    0.07
     sectors
    0.07
     Arabs
    0.07
     된
    0.07
     싸
    0.07
     auto's
    0.07
    Activations Density 0.001%

    No Known Activations