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. 15-RESID-POST-AA
    6. 19019
    Prev
    Next
    INDEX
    Explanations

    script dialogue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trekken
    -0.08
     הזאת
    -0.08
    .unsqueeze
    -0.08
    就在
    -0.08
    -thinking
    -0.08
    writing
    -0.08
    -lasting
    -0.07
    吃奶
    -0.07
     ajust
    -0.07
     thinking
    -0.07
    POSITIVE LOGITS
     आगामी
    0.08
     various
    0.08
     перечис
    0.08
    ائح
    0.08
     grievances
    0.08
     outlines
    0.08
     upcoming
    0.08
     рецеп
    0.07
     hình
    0.07
    (Client
    0.07
    Activations Density 0.016%

    No Known Activations