© 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. 63941
    Prev
    Next
    INDEX
    Explanations

    file inputs

    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
     breed
    -0.08
     pomp
    -0.08
     eld
    -0.08
     vot
    -0.08
    augmentation
    -0.07
     anna
    -0.07
     hemen
    -0.07
     breeds
    -0.07
     resort
    -0.07
     aligns
    -0.07
    POSITIVE LOGITS
    gäng
    0.09
    .try
    0.08
    <HTML
    0.08
    rene
    0.08
    tos
    0.08
    (se
    0.07
    oinen
    0.07
    ssis
    0.07
     profiling
    0.07
     patt
    0.07
    Activations Density 0.009%

    No Known Activations