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. 30803
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
     antibodies
    -0.08
    afrika
    -0.08
     purposes
    -0.07
    工商
    -0.07
    _mb
    -0.07
    灰
    -0.07
    705
    -0.07
    -0.07
    imet
    -0.07
    istical
    -0.07
    POSITIVE LOGITS
     gent
    0.09
     ausdrücklich
    0.09
    ضرورة
    0.09
    Greeting
    0.09
     παρουσία
    0.09
     politely
    0.08
     courteous
    0.08
     conversational
    0.08
     ակտիվ
    0.08
     greeting
    0.08
    Activations Density 0.001%

    No Known Activations