© 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. 3-RESID-POST-AA
    11. 12726
    Prev
    Next
    INDEX
    Explanations

    French language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rap
    -0.08
     ger
    -0.08
    Ger
    -0.07
    救
    -0.07
    Krist
    -0.07
     fungus
    -0.07
    -0.07
    Bi
    -0.07
    Agency
    -0.07
     resíduos
    -0.07
    POSITIVE LOGITS
     تعریف
    0.08
    �
    0.08
     정의
    0.07
     obec
    0.07
     गोल
    0.07
     utk
    0.07
     นิ
    0.07
     Sve
    0.07
     typ
    0.07
    ஞ
    0.07
    Activations Density 0.001%
    No Known Activations