© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 68536
    Prev
    Next
    INDEX
    Explanations

    Preventing overfitting

    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
     Tint
    -0.08
     sediments
    -0.08
    Tint
    -0.08
     авиа
    -0.08
     deity
    -0.08
     শত
    -0.08
     Atmos
    -0.08
     ধর্ম
    -0.08
     tinct
    -0.08
     transported
    -0.07
    POSITIVE LOGITS
    prevent
    0.10
    .fit
    0.10
     preventing
    0.10
    防
    0.09
     防
    0.09
     penal
    0.09
     overly
    0.09
     pruning
    0.09
    .dropout
    0.09
    Prevent
    0.09
    Activations Density 0.008%

    No Known Activations