© 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. 11-RESID-POST-AA
    11. 78153
    Prev
    Next
    INDEX
    Explanations

    cleaning and disinfection

    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
     DOS
    -0.08
     Participation
    -0.08
     билет
    -0.07
    (Query
    -0.07
    退休
    -0.07
     Python
    -0.07
    (Customer
    -0.07
    ulares
    -0.07
     reunited
    -0.07
     XML
    -0.07
    POSITIVE LOGITS
     disinfect
    0.12
     వైర
    0.11
     pathogens
    0.11
     бактер
    0.11
     microbes
    0.10
     antise
    0.10
     bacteria
    0.10
     ವೈರ
    0.10
     sprayed
    0.09
     инфек
    0.09
    Activations Density 0.014%

    No Known Activations