© 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. 108325
    Prev
    Next
    INDEX
    Explanations

    Labeling shapes with letters

    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
     Engagement
    -0.08
    ,args
    -0.08
     engagement
    -0.07
    	opts
    -0.07
    _MT
    -0.07
    Aus
    -0.07
    技能
    -0.07
     Aggreg
    -0.07
    _AVAILABLE
    -0.07
     Aus
    -0.07
    POSITIVE LOGITS
     esquina
    0.09
    laš
    0.08
     дыр
    0.08
    Disposed
    0.08
     товар
    0.08
     kav
    0.08
     左
    0.08
     kiri
    0.08
     fermer
    0.08
     ghe
    0.08
    Activations Density 0.020%

    No Known Activations