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. 65261
    Prev
    Next
    INDEX
    Explanations

    robotics

    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
     조회
    -0.10
     taut
    -0.08
    ════════
    -0.08
     objetivo
    -0.08
    ════
    -0.08
    cups
    -0.08
    Canadian
    -0.08
     expediente
    -0.07
     mandated
    -0.07
    ══
    -0.07
    POSITIVE LOGITS
     robotics
    0.13
     Robotics
    0.11
     autonomous
    0.11
     swarm
    0.10
    (robot
    0.10
     enthusiasts
    0.10
     servo
    0.10
     оснащ
    0.09
     sensors
    0.09
     Autonomous
    0.09
    Activations Density 0.011%

    No Known Activations