Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 88248
    Prev
    Next
    INDEX
    Explanations

    Encephalitis and sepsis

    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
     Crown
    -0.09
     selfish
    -0.08
    plink
    -0.08
     Located
    -0.08
     Yorker
    -0.08
     pout
    -0.07
     lever
    -0.07
     wła
    -0.07
     homeowner
    -0.07
    rive
    -0.07
    POSITIVE LOGITS
     inflam
    0.09
    Nep
    0.08
    .Event
    0.08
     Bridge
    0.08
     influenza
    0.08
    .from
    0.08
    Bridge
    0.08
     antibiotic
    0.08
    _Msp
    0.08
     Rodríguez
    0.08
    Activations Density 0.006%

    No Known Activations