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. 3-RESID-POST-AA
    6. 2023
    Prev
    Next
    INDEX
    Explanations

    kins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      ↵↵
    -0.07
     täh
    -0.07
    Plans
    -0.07
     stakes
    -0.07
     久
    -0.07
     serviced
    -0.07
    <Big
    -0.07
    Adv
    -0.07
     illuminated
    -0.07
     spar
    -0.07
    POSITIVE LOGITS
    ‌های
    0.09
    _callable
    0.09
     callable
    0.08
     patience
    0.08
     wit
    0.08
    herited
    0.08
     Senate
    0.08
    ‌ها
    0.07
     آب
    0.07
    اهي
    0.07
    Activations Density 0.004%

    No Known Activations