© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7979
    Prev
    Next
    INDEX
    Explanations

    Machine learning model training

    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
     despair
    -0.09
     여행
    -0.09
     mania
    -0.08
     reggae
    -0.08
     convey
    -0.08
     Cozy
    -0.08
     spas
    -0.08
     પ્રવાસ
    -0.08
    旅行
    -0.08
     prohibition
    -0.08
    POSITIVE LOGITS
     calibration
    0.12
     batching
    0.11
     refining
    0.11
     Calibration
    0.10
     accumulating
    0.10
    .Update
    0.10
     تحديث
    0.10
    _update
    0.10
     updating
    0.10
    Calibration
    0.10
    Activations Density 0.012%

    No Known Activations