© 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. 108691
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Laguna
    -0.09
     Montessori
    -0.09
     homeschool
    -0.08
     classrooms
    -0.08
     Toys
    -0.08
     Alaska
    -0.08
    	count
    -0.08
     bedrooms
    -0.08
     kittens
    -0.08
     cottage
    -0.08
    POSITIVE LOGITS
     chromat
    0.11
     cyclists
    0.10
     racing
    0.10
     skiing
    0.09
     cyclist
    0.09
    赛事
    0.09
     legion
    0.09
     선수
    0.09
     rider
    0.09
     swe
    0.09
    Activations Density 0.021%

    No Known Activations