© 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. 29594
    Prev
    Next
    INDEX
    Explanations

    imaginary unit problems

    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
    entropy
    -0.07
     ast
    -0.07
     Carrefour
    -0.07
     kang
    -0.07
     autonom
    -0.07
     KO
    -0.07
    Rice
    -0.07
    _lp
    -0.07
     Yum
    -0.07
    straight
    -0.07
    POSITIVE LOGITS
    �
    0.08
     Wel
    0.08
     bezahlt
    0.08
    毁
    0.07
     والتر
    0.07
     sequencing
    0.07
     sixty
    0.07
    Corona
    0.07
    Vintage
    0.07
     soutenir
    0.07
    Activations Density 0.129%

    No Known Activations