© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8109
    Prev
    Next
    INDEX
    Explanations

    ynthesis

    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
    ancer
    -0.08
    requested
    -0.08
     extremist
    -0.08
     ملک
    -0.08
    μένου
    -0.08
     Escorts
    -0.08
     vem
    -0.08
    档
    -0.08
    xm
    -0.08
     requested
    -0.07
    POSITIVE LOGITS
    方式
    0.09
    过程中
    0.09
     során
    0.09
    机制
    0.09
     nutrients
    0.08
     bacteria
    0.08
    过程
    0.08
     rainforest
    0.08
     ponder
    0.08
    公式
    0.08
    Activations Density 0.002%

    No Known Activations