© 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. 94550
    Prev
    Next
    INDEX
    Explanations

    math equations with letters

    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
     collide
    -0.08
    enges
    -0.07
     nafasi
    -0.07
     نسخة
    -0.07
    最准
    -0.07
     vers
    -0.07
     métallique
    -0.07
    ğinde
    -0.07
    elige
    -0.07
     Alum
    -0.07
    POSITIVE LOGITS
     répart
    0.10
     marriages
    0.09
    .Count
    0.09
    人口
    0.08
     koliko
    0.08
     populations
    0.08
    jumlah
    0.08
     jumlah
    0.08
     Cases
    0.08
    Jumlah
    0.08
    Activations Density 0.025%

    No Known Activations