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. 78715
    Prev
    Next
    INDEX
    Explanations

    number of divisors

    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
     Tick
    -0.08
     trenches
    -0.08
     priorities
    -0.08
    бу
    -0.08
     governments
    -0.08
     mesas
    -0.08
     Governments
    -0.07
    domains
    -0.07
    tren
    -0.07
    -ab
    -0.07
    POSITIVE LOGITS
    Aantal
    0.11
     count
    0.11
    Número
    0.10
     counting
    0.10
    Количество
    0.09
     تعداد
    0.09
    count
    0.09
     COUNT
    0.09
    Counting
    0.09
     എണ്ണം
    0.09
    Activations Density 0.023%

    No Known Activations