© 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. 23-RESID-POST-AA
    11. 96466
    Prev
    Next
    INDEX
    Explanations

    neuroscience and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     putih
    -0.08
     C
    -0.08
     ail
    -0.07
     episodes
    -0.07
     Rudy
    -0.07
     blaming
    -0.07
     gol
    -0.07
    jeb
    -0.07
    _force
    -0.07
    adi
    -0.07
    POSITIVE LOGITS
     всему
    0.09
     sämtliche
    0.08
    ous
    0.08
    배
    0.07
    ously
    0.07
    Newsletter
    0.07
    Podcast
    0.07
    BM
    0.07
    Bass
    0.07
    Coupon
    0.07
    Activations Density 0.000%

    No Known Activations