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. 43555
    Prev
    Next
    INDEX
    Explanations

    pulled pork

    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
     starch
    -0.09
     formulation
    -0.08
    πεζ
    -0.08
    stride
    -0.08
     безопасности
    -0.08
    illong
    -0.08
     solv
    -0.08
    .Const
    -0.08
     안전
    -0.08
     발생
    -0.08
    POSITIVE LOGITS
    Twe
    0.08
     hooks
    0.08
     Ranch
    0.08
     AWS
    0.08
     BBQ
    0.08
    Traffic
    0.07
     tricks
    0.07
     ట్వ
    0.07
     barbecue
    0.07
     Extreme
    0.07
    Activations Density 0.008%

    No Known Activations