© 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. 47310
    Prev
    Next
    INDEX
    Explanations

    problem

    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
    Savings
    -0.09
     Savings
    -0.08
     calculations
    -0.08
     savings
    -0.08
     commas
    -0.08
    amin
    -0.08
     ஈ
    -0.08
     сделки
    -0.08
     tasse
    -0.07
     prices
    -0.07
    POSITIVE LOGITS
     outlined
    0.09
     cops
    0.08
     Thou
    0.08
     UIL
    0.08
    Outline
    0.08
     refine
    0.08
    ,module
    0.08
     komunit
    0.08
    (tasks
    0.08
    日晚
    0.07
    Activations Density 0.030%

    No Known Activations