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. 98574
    Prev
    Next
    INDEX
    Explanations

    UI design

    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
     bénévol
    -0.09
     béné
    -0.08
    _wsgi
    -0.08
    NETWORK
    -0.08
     wrestler
    -0.08
    routers
    -0.07
    TERS
    -0.07
     nasil
    -0.07
    .servlet
    -0.07
    Transpose
    -0.07
    POSITIVE LOGITS
     Chakra
    0.16
    chakra
    0.15
     Material
    0.15
     Story
    0.15
     Atomic
    0.15
     atomic
    0.14
     Ant
    0.14
    Story
    0.13
     chakra
    0.13
    Material
    0.13
    Activations Density 0.009%

    No Known Activations