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. 49304
    Prev
    Next
    INDEX
    Explanations

    Quantities from another item

    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
    βολ
    -0.08
    лес
    -0.08
     неприят
    -0.08
     synch
    -0.07
    Selected
    -0.07
    abra
    -0.07
     തിരഞ്ഞെട
    -0.07
    äs
    -0.07
    bre
    -0.07
     begro
    -0.07
    POSITIVE LOGITS
     usable
    0.10
     تقس
    0.10
     beradi
    0.10
    usable
    0.09
     reusable
    0.09
     yield
    0.09
     daraus
    0.09
     Recipe
    0.09
     δυνατό
    0.08
    	yield
    0.08
    Activations Density 0.022%

    No Known Activations