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. 77489
    Prev
    Next
    INDEX
    Explanations

    Ham Sandwich Theorem

    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
    иски
    -0.08
     creep
    -0.08
     кін
    -0.08
     kl
    -0.08
     prevented
    -0.08
     machte
    -0.07
     moteur
    -0.07
     stored
    -0.07
    SSFCell
    -0.07
    履
    -0.07
    POSITIVE LOGITS
     glove
    0.09
    -balanced
    0.08
     Bal
    0.08
    balance
    0.08
    Balances
    0.08
     CUT
    0.08
     Balance
    0.08
    knife
    0.08
     Ambos
    0.08
     Dove
    0.08
    Activations Density 0.007%

    No Known Activations