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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 131014
    Prev
    Next
    INDEX
    Explanations

    Qt Quick and animations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     крест
    -0.09
     clubes
    -0.08
     zwart
    -0.08
     ด
    -0.08
     ов
    -0.08
    _core
    -0.08
     brown
    -0.08
    console
    -0.08
     سفید
    -0.08
    crc
    -0.08
    POSITIVE LOGITS
     Scene
    0.12
    .scene
    0.11
    Scene
    0.11
     Scenes
    0.10
     scene
    0.10
     Shader
    0.10
    	Scene
    0.10
    声明
    0.10
    _scene
    0.10
    ML
    0.10
    Activations Density 0.003%

    No Known Activations