© 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. 70085
    Prev
    Next
    INDEX
    Explanations

    explosives

    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
     bundles
    -0.08
     dimension
    -0.07
    dim
    -0.07
    bout
    -0.07
     dimensions
    -0.07
    Bundles
    -0.07
    .dimension
    -0.07
    Dimensions
    -0.07
    _bundle
    -0.07
    -tax
    -0.07
    POSITIVE LOGITS
     demol
    0.09
    剤
    0.09
    合同
    0.08
    撃
    0.08
    犯罪
    0.08
     primers
    0.08
     okwu
    0.08
     welding
    0.08
     odstr
    0.08
     demolition
    0.08
    Activations Density 0.005%

    No Known Activations