Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 77398
    Prev
    Next
    INDEX
    Explanations

    digestion

    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
    Quiet
    -0.08
     understated
    -0.08
     quit
    -0.08
    .off
    -0.07
    Quit
    -0.07
    bre
    -0.07
     encourage
    -0.07
    励
    -0.07
     volts
    -0.07
    Bre
    -0.07
    POSITIVE LOGITS
     digestion
    0.14
     digestive
    0.12
     пищи
    0.12
     খাব
    0.11
    евар
    0.11
     пищ
    0.11
     saliva
    0.10
     খাদ
    0.10
     भोजन
    0.10
     maaltijd
    0.10
    Activations Density 0.005%

    No Known Activations