© 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. 108452
    Prev
    Next
    INDEX
    Explanations

    gain

    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
     bora
    -0.08
     improving
    -0.08
     arrays
    -0.08
    ères
    -0.08
     bosque
    -0.08
     thrilled
    -0.07
     বিজ
    -0.07
     forbed
    -0.07
    灭
    -0.07
    דה
    -0.07
    POSITIVE LOGITS
     accumulation
    0.12
     buildup
    0.10
    增长
    0.10
    Accum
    0.09
     accumulating
    0.09
    增加
    0.09
     증가
    0.09
     ingestion
    0.08
     incurred
    0.08
    enis
    0.08
    Activations Density 0.011%

    No Known Activations