© 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. 113391
    Prev
    Next
    INDEX
    Explanations

    quarterly

    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
    ikon
    -0.08
     هنگام
    -0.08
    icted
    -0.08
    ленный
    -0.08
     совсем
    -0.08
     لقد
    -0.08
    ленная
    -0.08
    _low
    -0.08
     combustible
    -0.07
    wanted
    -0.07
    POSITIVE LOGITS
    마다
    0.10
    检查
    0.09
     revisar
    0.09
     പരിശോധ
    0.09
    评
    0.09
     समीक्षा
    0.08
    씩
    0.08
     refres
    0.08
     checkpoint
    0.08
    报告
    0.08
    Activations Density 0.033%

    No Known Activations