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. 11-RESID-POST-AA
    6. 58606
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    .GR
    -0.08
    Vault
    -0.08
     Bologna
    -0.08
    ocumented
    -0.08
    ENCE
    -0.07
     Clarkson
    -0.07
     Mona
    -0.07
     Kinect
    -0.07
    	scope
    -0.07
    GST
    -0.07
    POSITIVE LOGITS
     arranged
    0.08
    -aga
    0.08
     micron
    0.08
     Double
    0.08
    �
    0.08
    淡
    0.07
     doubled
    0.07
     Doub
    0.07
     Crypto
    0.07
     ude
    0.07
    Activations Density 0.251%

    No Known Activations