© 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. 69674
    Prev
    Next
    INDEX
    Explanations

    Date

    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
    -Bar
    -0.08
     Cant
    -0.08
    Bye
    -0.07
     BL
    -0.07
     DL
    -0.07
     structural
    -0.07
    .experimental
    -0.07
    CHAN
    -0.07
     Fly
    -0.07
    дим
    -0.07
    POSITIVE LOGITS
     кален
    0.08
    oworld
    0.08
     世界
    0.08
    world
    0.08
     пром
    0.08
     객체
    0.08
    picker
    0.08
    0.08
    cstdio
    0.07
     palpable
    0.07
    Activations Density 0.003%

    No Known Activations