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. 60504
    Prev
    Next
    INDEX
    Explanations

    coding dependencies

    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
    料理
    -0.08
     desp
    -0.08
    extent
    -0.08
     prevenir
    -0.08
    neden
    -0.07
    ارع
    -0.07
    -runtime
    -0.07
    ön
    -0.07
     предотвращ
    -0.07
     offensichtlich
    -0.07
    POSITIVE LOGITS
    `.↵
    0.08
    ("")]↵
    0.08
     UDP
    0.07
     Base
    0.07
     sporty
    0.07
     bond
    0.07
     ಬ್ಯ
    0.07
     Bond
    0.07
    uated
    0.07
     (↵
    0.07
    Activations Density 0.001%

    No Known Activations