© 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. 68793
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    érant
    -0.08
    orm
    -0.08
    heg
    -0.08
    stätten
    -0.08
     lob
    -0.08
     prima
    -0.07
    通常
    -0.07
    cljs
    -0.07
     Georg
    -0.07
     Osborne
    -0.07
    POSITIVE LOGITS
     আগামী
    0.09
     eksper
    0.08
     ekspert
    0.07
     эксперт
    0.07
     Liu
    0.07
     terbaru
    0.07
     moderately
    0.07
     fores
    0.07
    ىل
    0.07
     énergétique
    0.07
    Activations Density 0.004%

    No Known Activations