© 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. 94472
    Prev
    Next
    INDEX
    Explanations

    woman

    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
    _sq
    -0.07
    ema
    -0.07
    هوة
    -0.07
    _pages
    -0.07
     Français
    -0.07
     deutsche
    -0.07
    ред
    -0.07
    credito
    -0.07
    excerpt
    -0.07
     Vitamins
    -0.07
    POSITIVE LOGITS
     handeln
    0.08
     ಮು
    0.08
     يقوم
    0.08
    嘴
    0.08
     повед
    0.08
    ಳೆಯ
    0.08
    不停
    0.08
     تقوم
    0.08
     ಹಿಂದೆ
    0.08
     delante
    0.08
    Activations Density 0.007%

    No Known Activations