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. 88062
    Prev
    Next
    INDEX
    Explanations

    :

    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
    бр
    -0.08
     حرفه
    -0.08
    ബ്ര
    -0.08
     ಪ್ರಕ
    -0.08
     efficiently
    -0.08
     genuinely
    -0.08
    HAS
    -0.08
    ब्र
    -0.08
     LOW
    -0.08
     تخص
    -0.08
    POSITIVE LOGITS
    0.08
    grund
    0.07
    625
    0.07
     знамен
    0.07
     derivative
    0.07
    .tx
    0.07
     gn
    0.07
    ünkü
    0.07
    ut
    0.07
    _Manager
    0.07
    Activations Density 0.072%

    No Known Activations