© 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. 75574
    Prev
    Next
    INDEX
    Explanations

    trading

    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
    ylinder
    -0.09
    	range
    -0.08
    	Create
    -0.08
     contractor
    -0.08
    -Men
    -0.08
     Reis
    -0.08
     feat
    -0.08
     impregn
    -0.08
     Freder
    -0.07
     марки
    -0.07
    POSITIVE LOGITS
    走势
    0.12
     relationships
    0.11
    关系
    0.11
     relación
    0.11
    Relation
    0.11
    Relationship
    0.11
    Relationships
    0.11
    _relationship
    0.11
     relationship
    0.10
     correlations
    0.10
    Activations Density 0.006%

    No Known Activations