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. 65695
    Prev
    Next
    INDEX
    Explanations

    Hyphens

    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
     calendar
    -0.09
    ROWS
    -0.08
     MID
    -0.08
     crypto
    -0.08
     सेट
    -0.07
     expressions
    -0.07
     milestones
    -0.07
    .Unique
    -0.07
    igious
    -0.07
    祭
    -0.07
    POSITIVE LOGITS
     deviation
    0.09
    Deviation
    0.09
     Approx
    0.08
    Approx
    0.08
     desvi
    0.08
    عدم
    0.08
    лама
    0.08
     approxim
    0.08
     الاتصال
    0.08
     sedikit
    0.08
    Activations Density 0.014%

    No Known Activations