Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11762
    Prev
    Next
    INDEX
    Explanations

    final

    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
     Claudia
    -0.08
     Montage
    -0.08
     DUI
    -0.08
    sten
    -0.08
     clin
    -0.08
     regionale
    -0.08
    svoll
    -0.08
    archie
    -0.07
     Maintain
    -0.07
    edas
    -0.07
    POSITIVE LOGITS
     présentation
    0.09
     présenter
    0.08
     وړاندې
    0.07
    015
    0.07
     präsentieren
    0.07
     expectations
    0.07
     presentación
    0.07
     അവത
    0.07
     aspett
    0.07
     تار
    0.07
    Activations Density 0.011%

    No Known Activations