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. 111731
    Prev
    Next
    INDEX
    Explanations

    Mentions

    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
     Runner
    -0.08
     Young
    -0.08
     Seconds
    -0.08
     eingef
    -0.07
     Procedures
    -0.07
     Stopwatch
    -0.07
     Lieutenant
    -0.07
     Procedure
    -0.07
     Min
    -0.07
    tructor
    -0.07
    POSITIVE LOGITS
     sentiment
    0.11
     sentimento
    0.10
     sentimiento
    0.10
     mentioning
    0.10
     praising
    0.09
    mentions
    0.09
     sentiments
    0.09
     bouche
    0.09
     discussing
    0.09
    博客
    0.09
    Activations Density 0.028%

    No Known Activations