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. 8975
    Prev
    Next
    INDEX
    Explanations

    cap

    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
     Rab
    -0.08
     carc
    -0.08
    hour
    -0.08
    bg
    -0.08
    麼
    -0.07
     Lug
    -0.07
     Serg
    -0.07
    getitem
    -0.07
    sf
    -0.07
    Rab
    -0.07
    POSITIVE LOGITS
     oxid
    0.09
    illary
    0.08
     골
    0.07
     nhìn
    0.07
    咪
    0.07
     blown
    0.07
    0.07
     hed
    0.07
     sức
    0.07
     fas
    0.07
    Activations Density 0.016%

    No Known Activations