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. 42075
    Prev
    Next
    INDEX
    Explanations

    ing

    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
     Noah
    -0.09
    armes
    -0.09
     esteemed
    -0.08
     speeches
    -0.08
     astrology
    -0.08
     Qualität
    -0.08
    lus
    -0.08
     renowned
    -0.08
     πο
    -0.08
     qualidade
    -0.08
    POSITIVE LOGITS
     contiguous
    0.13
     consecutive
    0.10
     occupies
    0.09
     occupy
    0.09
     sites
    0.09
    Centered
    0.09
     diced
    0.09
     מתאים
    0.08
    Adjacent
    0.08
     snug
    0.08
    Activations Density 0.017%

    No Known Activations