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. 43452
    Prev
    Next
    INDEX
    Explanations

    label

    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
     تناول
    -0.09
     neeg
    -0.09
     플랫폼
    -0.08
     platform
    -0.08
     litoral
    -0.08
     specialist
    -0.07
     JSONArray
    -0.07
     spezial
    -0.07
     tunt
    -0.07
     empa
    -0.07
    POSITIVE LOGITS
    注明
    0.10
     Label
    0.10
     labeling
    0.10
     Labels
    0.09
     labels
    0.09
     붙
    0.09
     Bottom
    0.09
    _labels
    0.08
    _label
    0.08
     Inside
    0.08
    Activations Density 0.014%

    No Known Activations