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. 12202
    Prev
    Next
    INDEX
    Explanations

    volume/quantity

    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
    Left
    -0.08
     wandering
    -0.08
     temperament
    -0.08
     Left
    -0.08
     left
    -0.07
    guid
    -0.07
     Alive
    -0.07
    _left
    -0.07
     lively
    -0.07
     tecla
    -0.07
    POSITIVE LOGITS
     Discounts
    0.12
     скид
    0.11
     discounts
    0.11
    優惠
    0.10
    _discount
    0.10
     rebates
    0.10
    优惠
    0.10
     rebate
    0.09
     kredit
    0.09
    Discount
    0.09
    Activations Density 0.016%

    No Known Activations