© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96434
    Prev
    Next
    INDEX
    Explanations

    decide

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Initially
    -0.09
    'où
    -0.08
     sonrası
    -0.08
    ьд
    -0.08
     Usually
    -0.08
     Initial
    -0.08
     originally
    -0.08
     rechnen
    -0.08
     красивые
    -0.08
     initial
    -0.07
    POSITIVE LOGITS
     decidiu
    0.21
     décidé
    0.21
     decidió
    0.21
     decided
    0.20
     besloot
    0.20
     décider
    0.20
     decide
    0.19
     décide
    0.19
     decidir
    0.19
     decides
    0.18
    Activations Density 0.146%

    No Known Activations