© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29473
    Prev
    Next
    INDEX
    Explanations

    irritation

    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
    awasan
    -0.08
     Told
    -0.08
     William
    -0.08
     Biggest
    -0.08
    �
    -0.08
     timber
    -0.08
    forall
    -0.07
    ,the
    -0.07
     fotografía
    -0.07
    śc
    -0.07
    POSITIVE LOGITS
     irritation
    0.11
     irrit
    0.10
     irritated
    0.09
     inflammation
    0.09
     일
    0.08
    一下
    0.08
     impurities
    0.08
    can
    0.08
     مو
    0.07
     사항
    0.07
    Activations Density 0.003%

    No Known Activations