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. 117412
    Prev
    Next
    INDEX
    Explanations

    frame

    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
     egal
    -0.09
     toppings
    -0.09
     groceries
    -0.08
     affiliations
    -0.08
     foods
    -0.08
     produkty
    -0.08
     cov
    -0.08
    <ll
    -0.08
     wield
    -0.08
     topping
    -0.08
    POSITIVE LOGITS
    动画
    0.15
     animation
    0.13
     Animation
    0.13
    Animation
    0.13
    動畫
    0.13
    Animating
    0.13
    animation
    0.12
    (animation
    0.12
    _animation
    0.12
    -animation
    0.11
    Activations Density 0.010%

    No Known Activations