© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 95637
    Prev
    Next
    INDEX
    Explanations

    binomial coefficients

    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
     salon
    -0.09
     warmth
    -0.08
     chaleureux
    -0.08
     конферен
    -0.08
     SUVs
    -0.08
     PLC
    -0.08
     seekers
    -0.08
     пояс
    -0.08
     nightclub
    -0.08
     nightlife
    -0.08
    POSITIVE LOGITS
     ballot
    0.08
     Lucas
    0.08
    overflow
    0.08
    _vue
    0.08
    祖
    0.08
    Lucas
    0.08
     multin
    0.07
     �
    0.07
    Percent
    0.07
     factorial
    0.07
    Activations Density 0.013%

    No Known Activations