© 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. 43533
    Prev
    Next
    INDEX
    Explanations

    largest value

    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
    yside
    -0.08
    _less
    -0.08
    лях
    -0.08
    лаб
    -0.08
     bolsillo
    -0.08
    metic
    -0.08
     sided
    -0.07
    _spacing
    -0.07
    客户端
    -0.07
     dagdag
    -0.07
    POSITIVE LOGITS
     höchste
    0.12
     highest
    0.11
     ترین
    0.11
    highest
    0.11
     pinnacle
    0.10
    Highest
    0.10
     최고
    0.10
     maximize
    0.10
     hoogste
    0.10
    ‌ترین
    0.09
    Activations Density 0.036%

    No Known Activations