© 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. 71404
    Prev
    Next
    INDEX
    Explanations

    Model instructions and questions

    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
     declaring
    -0.08
     synchronized
    -0.08
     Isabel
    -0.07
    同期
    -0.07
     synchronize
    -0.07
     alone
    -0.07
    affen
    -0.07
     avenir
    -0.07
    Merc
    -0.07
     Merc
    -0.07
    POSITIVE LOGITS
     noqa
    0.08
    HAM
    0.08
     tasked
    0.08
     tiga
    0.08
    gericht
    0.08
    (metric
    0.07
     низ
    0.07
     вот
    0.07
     HIP
    0.07
    (""))
    0.07
    Activations Density 0.005%

    No Known Activations