Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88343
    Prev
    Next
    INDEX
    Explanations

    currency depreciation/cost increases

    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
     finalidad
    -0.08
     Spinner
    -0.08
    ografía
    -0.08
     Junction
    -0.08
     Encyclopedia
    -0.08
     Minimal
    -0.08
    .marker
    -0.08
    социа
    -0.08
    owels
    -0.07
    	spin
    -0.07
    POSITIVE LOGITS
     international
    0.09
     internationale
    0.09
    converted
    0.09
     internationaal
    0.09
     terug
    0.09
     converted
    0.09
     conversion
    0.09
    made
    0.08
     feitas
    0.08
    กลับ
    0.08
    Activations Density 0.009%

    No Known Activations