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. 49285
    Prev
    Next
    INDEX
    Explanations

    segment

    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
     spells
    -0.08
     prefixes
    -0.07
     cosplay
    -0.07
     भ्रम
    -0.07
     NATO
    -0.07
    Load
    -0.07
     എം
    -0.07
     नाम
    -0.07
     ?>"><
    -0.07
     compromising
    -0.07
    POSITIVE LOGITS
    等待
    0.08
     printemps
    0.08
     فوق
    0.08
     atraso
    0.08
    �
    0.08
     sorpresa
    0.08
     innovación
    0.07
     opposite
    0.07
    prise
    0.07
     protr
    0.07
    Activations Density 0.009%

    No Known Activations