© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64583
    Prev
    Next
    INDEX
    Explanations

    math symbols

    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
    .libs
    -0.08
     middleware
    -0.08
     mitten
    -0.08
    .om
    -0.07
    Nova
    -0.07
     Hond
    -0.07
    idin
    -0.07
    vs
    -0.07
    ernels
    -0.07
    ів
    -0.07
    POSITIVE LOGITS
     Δ
    0.08
    AGING
    0.08
     spanning
    0.08
    ，坚持
    0.07
    aurus
    0.07
    (source
    0.07
    umfang
    0.07
     extent
    0.07
    arası
    0.07
    átt
    0.07
    Activations Density 0.050%

    No Known Activations