© 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. 8028
    Prev
    Next
    INDEX
    Explanations

    graph theory

    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
     ratios
    -0.08
     ardh
    -0.08
    ittance
    -0.08
    比例
    -0.08
     inches
    -0.08
     Bank
    -0.08
     installment
    -0.08
     Villas
    -0.08
     scaled
    -0.07
    -0.07
    POSITIVE LOGITS
    neighbors
    0.09
     vertex
    0.08
    particip
    0.08
    人与
    0.08
     clique
    0.08
     adjacency
    0.08
    	n
    0.08
    Neighbors
    0.08
     neighbor
    0.08
     vertices
    0.08
    Activations Density 0.015%
    No Known Activations