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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 96802
    Prev
    Next
    INDEX
    Explanations

    Stirling number S(5,3)

    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
    ных
    -0.08
    냐
    -0.08
    128
    -0.08
    -integr
    -0.08
    -platform
    -0.08
     আহত
    -0.08
     lock
    -0.08
     criminals
    -0.08
    -high
    -0.08
    .high
    -0.08
    POSITIVE LOGITS
     fibonacci
    0.09
     pasan
    0.09
     Winston
    0.08
     Fib
    0.08
     expands
    0.08
     Fibonacci
    0.08
     Dennis
    0.08
     Sche
    0.08
     tlang
    0.08
     Expansion
    0.08
    Activations Density 0.007%

    No Known Activations