© 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. 78901
    Prev
    Next
    INDEX
    Explanations

    court

    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
    duration
    -0.09
     duration
    -0.08
    (duration
    -0.08
    elf
    -0.08
    	duration
    -0.08
     μ
    -0.08
     durée
    -0.08
     �
    -0.07
    -duration
    -0.07
     διάρκ
    -0.07
    POSITIVE LOGITS
     अदालत
    0.12
    法院
    0.11
     victories
    0.11
     মামলা
    0.10
     আদাল
    0.10
    判
    0.10
     lawsuit
    0.10
     unconstitutional
    0.10
     lawsuits
    0.10
     মাম
    0.10
    Activations Density 0.068%

    No Known Activations