© 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. 23-RESID-POST-AA
    11. 50610
    Prev
    Next
    INDEX
    Explanations

    banner ad sizes

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    headers
    -0.07
    cin
    -0.07
    cert
    -0.07
    .signal
    -0.07
     cardiovascular
    -0.07
    ола
    -0.07
    .memo
    -0.07
     headers
    -0.07
     Carne
    -0.07
    #+
    -0.07
    POSITIVE LOGITS
     donut
    0.09
    ponsored
    0.08
     crater
    0.08
     групп
    0.07
    ়
    0.07
    ್
    0.07
    گزاری
    0.07
    ikku
    0.07
     Nether
    0.07
    90
    0.07
    Activations Density 0.000%

    No Known Activations