© 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. 69040
    Prev
    Next
    INDEX
    Explanations

    2/3 or 1/3

    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
    ुलाई
    -0.08
     Stein
    -0.08
    Cer
    -0.07
     instincts
    -0.07
    ನವ
    -0.07
    सभा
    -0.07
     Eve
    -0.07
     दर्शन
    -0.07
    Italie
    -0.07
     istiq
    -0.07
    POSITIVE LOGITS
     Decimal
    0.08
     շ
    0.07
    pono
    0.07
     bry
    0.07
     Equal
    0.07
     Mp
    0.07
     seks
    0.07
    velle
    0.07
     bp
    0.07
     ukun
    0.07
    Activations Density 0.012%

    No Known Activations