© 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. 113670
    Prev
    Next
    INDEX
    Explanations

    grapheme characters

    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
     percaya
    -0.09
     Detail
    -0.08
     Dhabi
    -0.08
     geloof
    -0.08
     acreditar
    -0.08
     신규
    -0.08
     dst
    -0.08
     contagious
    -0.08
    (detail
    -0.08
     लगायत
    -0.07
    POSITIVE LOGITS
    commod
    0.08
     counting
    0.07
     olmay
    0.07
    bonjour
    0.07
     '
    0.07
     Zug
    0.07
     pí
    0.07
     permitted
    0.07
     mặt
    0.07
     linguistic
    0.07
    Activations Density 0.003%

    No Known Activations