Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9242
    Prev
    Next
    INDEX
    Explanations

    sum

    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
    olja
    -0.08
     Demokratie
    -0.08
    징
    -0.08
     欧美
    -0.08
    follow
    -0.08
     Democracy
    -0.08
     Folks
    -0.08
     Mensen
    -0.07
     RTV
    -0.07
     Xia
    -0.07
    POSITIVE LOGITS
     (-
    0.09
    ضاف
    0.07
    ارج
    0.07
     kenne
    0.07
     ordin
    0.07
     UIImage
    0.07
    ೀನ
    0.07
    yum
    0.07
     (+
    0.07
     ena
    0.07
    Activations Density 0.011%

    No Known Activations