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. 120419
    Prev
    Next
    INDEX
    Explanations

    reading

    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
    gehör
    -0.08
     principles
    -0.08
     Prinzip
    -0.08
     tudo
    -0.07
    Consider
    -0.07
    irected
    -0.07
    ๆ
    -0.07
     Bene
    -0.07
     Principle
    -0.07
    Alla
    -0.07
    POSITIVE LOGITS
    .onerror
    0.08
    过程中
    0.08
     akibat
    0.08
     squid
    0.08
     ਕਾਰ
    0.08
    时报
    0.08
     بسبب
    0.08
     betrekking
    0.08
    ikar
    0.08
     permitió
    0.08
    Activations Density 0.008%

    No Known Activations