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. 9108
    Prev
    Next
    INDEX
    Explanations

    neural networks

    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
    INST
    -0.08
     /*!↵
    -0.08
    _INST
    -0.08
     zainteres
    -0.08
     TAKE
    -0.08
     took
    -0.07
     synchron
    -0.07
     Leb
    -0.07
     ուղղ
    -0.07
     priori
    -0.07
    POSITIVE LOGITS
    ть
    0.08
     Cristo
    0.08
    cycl
    0.08
    Replace
    0.08
    Brief
    0.08
    fly
    0.08
     чего
    0.07
     Pequ
    0.07
    Coment
    0.07
    ьер
    0.07
    Activations Density 0.001%

    No Known Activations