Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78597
    Prev
    Next
    INDEX
    Explanations

    government contracts

    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
     resources
    -0.08
     ressources
    -0.08
     Cp
    -0.08
     Ressourcen
    -0.07
     contrairement
    -0.07
     eing
    -0.07
     displayed
    -0.07
     Olsen
    -0.07
     Coup
    -0.07
     Ome
    -0.07
    POSITIVE LOGITS
     clientele
    0.13
     заказ
    0.13
    采购
    0.11
     clienti
    0.11
     клиентов
    0.11
     opdrachtgever
    0.11
     ग्राह
    0.11
     buyers
    0.11
     مشتری
    0.11
    订单
    0.10
    Activations Density 0.102%

    No Known Activations