© 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. 3-RESID-POST-AA
    11. 2945
    Prev
    Next
    INDEX
    Explanations

    matrix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    貨
    -0.08
    \S
    -0.08
     societies
    -0.07
    פה
    -0.07
     batter
    -0.07
    כות
    -0.07
     lived
    -0.07
     bhith
    -0.07
     processor
    -0.07
    cors
    -0.07
    POSITIVE LOGITS
     Acne
    0.08
    491
    0.08
     Donovan
    0.08
     Yun
    0.07
    -invest
    0.07
     vomiting
    0.07
     supernatural
    0.07
     Shir
    0.07
    732
    0.07
    957
    0.07
    Activations Density 0.001%

    No Known Activations