© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44868
    Prev
    Next
    INDEX
    Explanations

    virus mutations and resistance

    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
     emos
    -0.08
     toned
    -0.08
     cups
    -0.08
     emotional
    -0.08
    credi
    -0.08
     crou
    -0.08
     Temple
    -0.08
    fill
    -0.07
     invitation
    -0.07
    Temple
    -0.07
    POSITIVE LOGITS
     resistant
    0.13
    -resistant
    0.13
     resistance
    0.13
     mutations
    0.12
     pathogenic
    0.12
    Resistance
    0.11
     Resistant
    0.11
     pathogens
    0.11
     Resistance
    0.11
     evade
    0.11
    Activations Density 0.011%

    No Known Activations