© 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. 129360
    Prev
    Next
    INDEX
    Explanations

    on

    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
     completos
    -0.08
     efectivos
    -0.08
     fiduci
    -0.07
     adaptés
    -0.07
     עצ
    -0.07
     fundamentais
    -0.07
     Appar
    -0.07
    'appar
    -0.07
     جيدة
    -0.07
     كاملة
    -0.07
    POSITIVE LOGITS
     namely
    0.12
     unnamed
    0.12
     namens
    0.11
     den
    0.10
     nam
    0.10
    叫
    0.10
     (`
    0.09
     называется
    0.09
     yakni
    0.09
     called
    0.09
    Activations Density 0.570%

    No Known Activations