© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29285
    Prev
    Next
    INDEX
    Explanations

    ambiguous 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
     cessation
    -0.10
    fü
    -0.09
     diagnosing
    -0.08
     hiz
    -0.08
    yş
    -0.08
     Balm
    -0.08
     emiss
    -0.08
     nearing
    -0.08
    termination
    -0.08
     convergence
    -0.08
    POSITIVE LOGITS
    Counting
    0.13
     Counting
    0.12
     permutations
    0.12
     counting
    0.12
     counted
    0.10
     restrictions
    0.10
    Permutation
    0.10
     factorial
    0.10
    Enumeration
    0.09
     combin
    0.09
    Activations Density 0.053%

    No Known Activations