© 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. 7478
    Prev
    Next
    INDEX
    Explanations

    scratchpad math problem-solving

    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
     unut
    -0.08
     pursuant
    -0.08
     detention
    -0.08
     importance
    -0.07
     thorough
    -0.07
     vuln
    -0.07
     compréhension
    -0.07
     cé
    -0.07
     legitimacy
    -0.07
     dile
    -0.07
    POSITIVE LOGITS
     Fibonacci
    0.08
     fibonacci
    0.08
    -ID
    0.08
     seem
    0.08
     parecía
    0.08
     Fuss
    0.08
     gebleven
    0.08
     seems
    0.07
    _dn
    0.07
     fuzzy
    0.07
    Activations Density 0.027%

    No Known Activations