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. 49338
    Prev
    Next
    INDEX
    Explanations

    waiver

    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
    刺
    -0.09
    forming
    -0.07
     interface
    -0.07
     гости
    -0.07
    213
    -0.07
     forming
    -0.07
    (i
    -0.07
     ciel
    -0.07
    мер
    -0.07
    	app
    -0.07
    POSITIVE LOGITS
     Buddhism
    0.08
    fsm
    0.08
     doctr
    0.08
    écn
    0.08
     slipper
    0.08
     Utils
    0.08
     Acre
    0.08
     tuku
    0.08
     Buk
    0.08
    况
    0.08
    Activations Density 0.001%

    No Known Activations