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. 49315
    Prev
    Next
    INDEX
    Explanations

    Measurement of length

    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
     recorded
    -0.08
     probabilities
    -0.08
     ಧ
    -0.08
     sau
    -0.08
     grains
    -0.08
     uży
    -0.07
     yö
    -0.07
     statue
    -0.07
     kwart
    -0.07
     Edge
    -0.07
    POSITIVE LOGITS
    award
    0.08
    anejo
    0.08
     Dedicated
    0.08
    Thai
    0.08
    Expandable
    0.08
     stroller
    0.08
    Dedicated
    0.08
     expandable
    0.08
     Flere
    0.08
     waterfront
    0.08
    Activations Density 0.013%

    No Known Activations