© 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. 25915
    Prev
    Next
    INDEX
    Explanations

    as

    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
    Vitals
    -0.08
    Mate
    -0.08
    sob
    -0.08
     Erfol
    -0.08
     iced
    -0.08
    accent
    -0.07
    successful
    -0.07
    fatal
    -0.07
     Amish
    -0.07
    دمت
    -0.07
    POSITIVE LOGITS
    荡
    0.09
     �
    0.08
     يتعلق
    0.08
    人为
    0.08
     fluctuate
    0.08
     Cait
    0.08
     grap
    0.08
     sujeito
    0.08
     ஸ
    0.07
    读
    0.07
    Activations Density 0.004%

    No Known Activations