© 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. 555
    Prev
    Next
    INDEX
    Explanations

    Foreign language technical texts

    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
    घर
    -0.08
    לק
    -0.08
    พ่
    -0.08
     명
    -0.08
    ახ
    -0.08
    981
    -0.07
     rêve
    -0.07
     droom
    -0.07
     第一
    -0.07
     Myst
    -0.07
    POSITIVE LOGITS
     approaches
    0.13
     approach
    0.12
     Vorge
    0.12
     Approach
    0.12
     abordagem
    0.12
     yaklaş
    0.12
    Appro
    0.11
     approche
    0.10
     APPRO
    0.10
     подход
    0.10
    Activations Density 0.006%

    No Known Activations