© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 99344
    Prev
    Next
    INDEX
    Explanations

    flavor

    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
    Baseline
    -0.09
     માણસ
    -0.08
     seorang
    -0.08
     onye
    -0.08
     voorsp
    -0.08
     wichtigste
    -0.08
     predict
    -0.08
     poverty
    -0.08
    ldre
    -0.08
     સૌથી
    -0.08
    POSITIVE LOGITS
     flavor
    0.12
     fragrance
    0.12
     scents
    0.12
     flavored
    0.11
     sabores
    0.11
     flavors
    0.11
     Geschmack
    0.11
     fragrances
    0.11
     flavorful
    0.10
     scented
    0.10
    Activations Density 0.042%

    No Known Activations