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. 117537
    Prev
    Next
    INDEX
    Explanations

    root

    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
     оснащ
    -0.08
    Leaving
    -0.07
    ்வ
    -0.07
    ảo
    -0.07
    ateau
    -0.07
    ractions
    -0.07
     пере
    -0.07
    .echo
    -0.07
    882
    -0.07
     counters
    -0.07
    POSITIVE LOGITS
    入口
    0.13
    /root
    0.11
     Root
    0.11
     root
    0.10
    .Root
    0.10
    _root
    0.10
    [root
    0.10
    (ROOT
    0.10
    	root
    0.10
    .root
    0.10
    Activations Density 0.009%

    No Known Activations