© 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. 110443
    Prev
    Next
    INDEX
    Explanations

    Base64 encoding/decoding

    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
    ества
    -0.08
    景
    -0.08
     Right
    -0.07
    Right
    -0.07
    late
    -0.07
     española
    -0.07
    exper
    -0.07
     right
    -0.07
    .right
    -0.07
     "
    -0.07
    POSITIVE LOGITS
     kaban
    0.09
     bookmaker
    0.09
     caretaker
    0.08
     wij
    0.08
    ्नी
    0.08
     بأن
    0.08
     empath
    0.08
     konsa
    0.08
     kundi
    0.08
    hlah
    0.08
    Activations Density 0.000%

    No Known Activations