© 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. 29719
    Prev
    Next
    INDEX
    Explanations

    applique

    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
     dizziness
    -0.08
     Gracias
    -0.08
    -Test
    -0.08
    幕后
    -0.08
    -0.08
     schrij
    -0.08
     Þegar
    -0.07
    	So
    -0.07
    _tx
    -0.07
     Observe
    -0.07
    POSITIVE LOGITS
     lettering
    0.09
    IH
    0.08
    patch
    0.08
     agregar
    0.08
    olt
    0.07
     patches
    0.07
     patch
    0.07
     pau
    0.07
     Northwest
    0.07
    OH
    0.07
    Activations Density 0.004%
    No Known Activations