© 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. 112360
    Prev
    Next
    INDEX
    Explanations

    sponge

    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
    auto
    -0.08
    'autre
    -0.07
    dir
    -0.07
     Git
    -0.07
    bp
    -0.07
    .auto
    -0.07
     legal
    -0.07
    aka
    -0.07
    misc
    -0.07
     લ
    -0.07
    POSITIVE LOGITS
     blitz
    0.10
    Ы
    0.09
    র্ধ
    0.09
    েষ
    0.09
    নার
    0.08
     heg
    0.08
    স্য
    0.08
    োভ
    0.08
    орма
    0.08
    естиваль
    0.08
    Activations Density 0.000%

    No Known Activations