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. 105989
    Prev
    Next
    INDEX
    Explanations

    medical procedures

    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
     grime
    -0.09
     Nikol
    -0.08
     nltk
    -0.08
     Azerba
    -0.08
     pollutants
    -0.08
    Vectors
    -0.08
    ಿಕ್ಕ
    -0.08
     Illustrator
    -0.08
     merc
    -0.08
     pathetic
    -0.08
    POSITIVE LOGITS
     advocated
    0.10
     guideline
    0.10
     postoperative
    0.10
     prophyl
    0.10
     controversial
    0.09
    Coordinator
    0.09
     خيار
    0.09
    Baseline
    0.09
     guidelines
    0.08
     surgeon
    0.08
    Activations Density 0.026%

    No Known Activations