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. 48976
    Prev
    Next
    INDEX
    Explanations

    ATP production

    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
     agre
    -0.08
    domin
    -0.08
    Domin
    -0.08
     desire
    -0.08
     directora
    -0.07
    'administration
    -0.07
     domine
    -0.07
     {*
    -0.07
     accented
    -0.07
     trendy
    -0.07
    POSITIVE LOGITS
    .count
    0.09
     attendu
    0.08
     Protein
    0.08
     تعداد
    0.08
     erwarten
    0.08
     Fowler
    0.08
     συνο
    0.08
     protein
    0.08
    Количество
    0.08
     Whe
    0.08
    Activations Density 0.004%

    No Known Activations