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. 77800
    Prev
    Next
    INDEX
    Explanations

    Acceleration and speed

    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
     slowly
    -0.09
     slow
    -0.09
     laz
    -0.09
     Slowly
    -0.08
     shag
    -0.08
     धीरे
    -0.08
     ż
    -0.08
     धी
    -0.08
     dull
    -0.08
    ующее
    -0.08
    POSITIVE LOGITS
     Luciano
    0.08
    rf
    0.08
     Plato
    0.07
     EXISTS
    0.07
    уме
    0.07
     foyer
    0.07
     Possible
    0.07
    ews
    0.07
    ="{
    0.07
     Exists
    0.07
    Activations Density 0.087%

    No Known Activations