© 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. 8199
    Prev
    Next
    INDEX
    Explanations

    History/Geography

    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
     Assamese
    -0.09
    bear
    -0.08
     western
    -0.08
    -prov
    -0.08
     Violet
    -0.08
     athe
    -0.08
     Mary's
    -0.07
     Marathi
    -0.07
     ty
    -0.07
     researcher
    -0.07
    POSITIVE LOGITS
     Именно
    0.09
    Cooldown
    0.08
     وبالتالي
    0.07
     cooldown
    0.07
    用于
    0.07
    Dual
    0.07
     جهت
    0.07
    ombies
    0.07
     permettent
    0.07
     Apk
    0.07
    Activations Density 0.062%

    No Known Activations