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. 44197
    Prev
    Next
    INDEX
    Explanations

    y

    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
    柜
    -0.08
     Thür
    -0.08
     kräft
    -0.08
    pile
    -0.08
    เต็ม
    -0.07
     retirees
    -0.07
    _INTEGER
    -0.07
     Croatia
    -0.07
     leaning
    -0.07
    GEST
    -0.07
    POSITIVE LOGITS
     plotting
    0.10
    .plot
    0.09
    _plot
    0.09
    оскоп
    0.08
    Plot
    0.08
     Hero
    0.08
     внес
    0.08
    uteurs
    0.07
    .axes
    0.07
     нанес
    0.07
    Activations Density 0.016%

    No Known Activations