© 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. 71255
    Prev
    Next
    INDEX
    Explanations

    armor and clothing descriptions

    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
     income
    -0.09
     incumb
    -0.08
     enterprise
    -0.08
     pensions
    -0.08
    Planning
    -0.08
    Fixture
    -0.08
     Planning
    -0.08
    Entre
    -0.08
     charter
    -0.08
     docket
    -0.08
    POSITIVE LOGITS
    (reinterpret
    0.10
     sleek
    0.10
    纹
    0.09
    FLAGS
    0.09
     translucent
    0.09
    Extern
    0.09
     camouflage
    0.09
    tos
    0.09
     Sakura
    0.08
     silhouettes
    0.08
    Activations Density 0.033%

    No Known Activations