© 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. 129505
    Prev
    Next
    INDEX
    Explanations

    /

    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
     pó
    -0.09
    智
    -0.08
     mathematical
    -0.08
    idue
    -0.08
     hvilke
    -0.08
     Bootstrap
    -0.08
    .bootstrap
    -0.07
    äki
    -0.07
     Mathematical
    -0.07
    iché
    -0.07
    POSITIVE LOGITS
     snelheid
    0.11
     Geschwindigkeit
    0.10
     скорости
    0.10
     velocidade
    0.10
     vitesse
    0.10
     speeds
    0.10
     velocidad
    0.09
    速度
    0.09
    speed
    0.09
     tốc
    0.09
    Activations Density 0.018%

    No Known Activations