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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103420
    Prev
    Next
    INDEX
    Explanations

    Interferon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lunch
    -0.07
    购物
    -0.07
     bum
    -0.07
    édie
    -0.07
    ulp
    -0.07
     ambapo
    -0.07
     parsing
    -0.07
     fuel
    -0.07
     körper
    -0.07
    ariş
    -0.07
    POSITIVE LOGITS
     interfer
    0.23
     IF
    0.20
    _IF
    0.17
    IF
    0.16
    (IF
    0.16
     antiviral
    0.16
     interfere
    0.14
     INTER
    0.14
    .IF
    0.13
     इंटर
    0.13
    Activations Density 0.003%

    No Known Activations