© 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. 29256
    Prev
    Next
    INDEX
    Explanations

    away

    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
     mans
    -0.08
    HIR
    -0.08
     jb
    -0.07
    .generate
    -0.07
    formance
    -0.07
     под
    -0.07
    Proof
    -0.07
     estan
    -0.07
    Perf
    -0.07
     takes
    -0.07
    POSITIVE LOGITS
     사항
    0.09
    事項
    0.08
    几点
    0.08
     Margin
    0.08
    区别
    0.08
    措施
    0.08
    ként
    0.08
    秘诀
    0.08
    ✔
    0.08
    κτη
    0.08
    Activations Density 0.002%

    No Known Activations