© 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. 54898
    Prev
    Next
    INDEX
    Explanations

    tangent

    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
     Montessori
    -0.08
     Codable
    -0.08
     Clay
    -0.07
     toh
    -0.07
     aporta
    -0.07
    Bak
    -0.07
     aerobic
    -0.07
     improvements
    -0.07
     �
    -0.07
     കാര്യ
    -0.07
    POSITIVE LOGITS
     illegally
    0.09
     соверш
    0.09
    miss
    0.08
     Fang
    0.08
     determin
    0.08
    .cover
    0.08
    于
    0.08
    於
    0.08
    isinin
    0.08
     સેવા
    0.07
    Activations Density 0.017%

    No Known Activations