© 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. 113470
    Prev
    Next
    INDEX
    Explanations

    Ziggurats

    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
     experimented
    -0.08
     búsqueda
    -0.08
     பே
    -0.08
     سابق
    -0.07
     معیار
    -0.07
    TTY
    -0.07
    orderby
    -0.07
     براي
    -0.07
    zufügen
    -0.07
     Titanium
    -0.07
    POSITIVE LOGITS
    okens
    0.09
    aunch
    0.08
    	cell
    0.08
     mound
    0.08
     quake
    0.08
     passport
    0.08
     mario
    0.08
    싶
    0.08
     mike
    0.08
     mase
    0.07
    Activations Density 0.000%

    No Known Activations