© 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. 69417
    Prev
    Next
    INDEX
    Explanations

    crushing

    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
     Liebe
    -0.08
    몰
    -0.08
     Andal
    -0.08
    लोक
    -0.07
     rubber
    -0.07
    اضة
    -0.07
     romantic
    -0.07
     Sty
    -0.07
    clinical
    -0.07
     anxiety
    -0.07
    POSITIVE LOGITS
     York
    0.08
    组件
    0.08
     crushers
    0.08
     workloads
    0.07
     Pivot
    0.07
    WAYS
    0.07
     ores
    0.07
     reductions
    0.07
     waw
    0.07
    ピ
    0.07
    Activations Density 0.006%

    No Known Activations