© 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. 68228
    Prev
    Next
    INDEX
    Explanations

    M

    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
    _DOCUMENT
    -0.08
     Jedi
    -0.08
     ～
    -0.08
     удов
    -0.08
     yana
    -0.08
     الأساسي
    -0.07
     Acho
    -0.07
     beý
    -0.07
    ("__
    -0.07
     杨
    -0.07
    POSITIVE LOGITS
     distort
    0.09
     predis
    0.08
     distortion
    0.08
     slump
    0.08
     inclin
    0.08
     solids
    0.08
    143
    0.07
    .collider
    0.07
     lån
    0.07
     pregunt
    0.07
    Activations Density 0.001%

    No Known Activations