© 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. 19-RESID-POST-AA
    11. 18746
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.10
    -based
    -0.10
    :
    -0.09
     blevet
    -0.09
    .^
    -0.09
    .Please
    -0.09
    .[
    -0.09
     của
    -0.09
    就是
    -0.08
    .This
    -0.08
    POSITIVE LOGITS
     they
    0.16
     они
    0.14
     ისინი
    0.14
     նրանք
    0.14
     אנו
    0.13
     вони
    0.13
     הם
    0.12
     if
    0.12
     þeir
    0.12
     it
    0.12
    Activations Density 0.008%

    No Known Activations