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. 11596
    Prev
    Next
    INDEX
    Explanations

    bug reporting

    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
     décisions
    -0.09
     concess
    -0.09
     dominance
    -0.08
     collegiate
    -0.08
     regulating
    -0.08
     регули
    -0.08
     फैसला
    -0.08
     entscheidet
    -0.08
     decisiones
    -0.08
     الغذائية
    -0.08
    POSITIVE LOGITS
     reproduc
    0.14
     reproduce
    0.12
     reprodu
    0.11
     reproduced
    0.11
    截图
    0.11
     screenshots
    0.10
     reproduction
    0.10
     screenshot
    0.10
     replication
    0.10
     reprodução
    0.10
    Activations Density 0.023%

    No Known Activations