© 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. 43000
    Prev
    Next
    INDEX
    Explanations

    statistical models and regressions

    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
     credentials
    -0.08
    ょう
    -0.08
     rato
    -0.08
    cipher
    -0.08
     �
    -0.08
     estup
    -0.08
    (bt
    -0.08
    ává
    -0.08
     wick
    -0.08
    credentials
    -0.08
    POSITIVE LOGITS
     biases
    0.11
     bias
    0.11
    Bias
    0.10
     Bias
    0.10
    .bias
    0.09
    bias
    0.09
    _bias
    0.08
     biais
    0.08
     fluctuations
    0.08
     ramach
    0.08
    Activations Density 0.001%

    No Known Activations