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. 112795
    Prev
    Next
    INDEX
    Explanations

    Aviation fuel efficiency

    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
    ிக்கப்பட்ட
    -0.08
     numbering
    -0.08
     bạn
    -0.08
     경찰
    -0.08
     पुलिस
    -0.08
     happenings
    -0.08
    .every
    -0.08
     mex
    -0.08
     Justice
    -0.07
     commissioners
    -0.07
    POSITIVE LOGITS
    优化
    0.12
     optimized
    0.11
     cruising
    0.11
    Flight
    0.11
     उड़
    0.11
    效率
    0.11
     flight
    0.10
    บิน
    0.10
    .optimize
    0.10
    optimized
    0.10
    Activations Density 0.010%

    No Known Activations