© 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. 29586
    Prev
    Next
    INDEX
    Explanations

    currency conversion, numbers

    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
     printk
    -0.09
     curricular
    -0.08
    .Setter
    -0.08
     conduce
    -0.08
    Configurations
    -0.08
    Enumer
    -0.08
    социа
    -0.08
     Reno
    -0.08
     Curriculum
    -0.07
     Robbins
    -0.07
    POSITIVE LOGITS
     converted
    0.15
    converted
    0.14
    金额
    0.13
     translated
    0.12
     montant
    0.12
     traduit
    0.12
     traduction
    0.12
     conversion
    0.12
     money
    0.11
    Converted
    0.11
    Activations Density 0.018%

    No Known Activations