© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26569
    Prev
    Next
    INDEX
    Explanations

    depth

    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
     adverse
    -0.08
    Rem
    -0.08
    Conven
    -0.07
     antiviral
    -0.07
    Prevent
    -0.07
    _rem
    -0.07
     Prevent
    -0.07
     antiv
    -0.07
     atract
    -0.07
     antic
    -0.07
    POSITIVE LOGITS
     grayscale
    0.11
     영상
    0.09
    纹
    0.09
    .Depth
    0.09
    ensity
    0.08
     stereo
    0.08
     viewer
    0.08
    /maps
    0.08
    outube
    0.08
     raster
    0.08
    Activations Density 0.006%

    No Known Activations