Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 54166
    Prev
    Next
    INDEX
    Explanations

    Redoing/repeating

    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
     Employ
    -0.08
    ilhar
    -0.08
     employing
    -0.08
     employ
    -0.08
    藏
    -0.08
    'Am
    -0.07
    *******/↵
    -0.07
    购
    -0.07
     magma
    -0.07
     Mazda
    -0.07
    POSITIVE LOGITS
     unfinished
    0.09
     இன்ன
    0.09
     ఇంకా
    0.08
     katk
    0.08
     կամ
    0.08
    履
    0.07
     დაგ
    0.07
     обязательно
    0.07
    TASK
    0.07
    Cb
    0.07
    Activations Density 0.000%

    No Known Activations