© 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. 7-RESID-POST-AA
    11. 891
    Prev
    Next
    INDEX
    Explanations

    labels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fountains
    -0.08
    -0.08
     knight
    -0.08
     seeded
    -0.07
     tweet
    -0.07
    IRQ
    -0.07
    (interval
    -0.07
    Ping
    -0.07
    .column
    -0.07
     Twitter
    -0.07
    POSITIVE LOGITS
    manufacturer
    0.10
    注明
    0.10
     Pharmaceutical
    0.09
     výrob
    0.09
     fabricante
    0.09
     Biod
    0.09
     biode
    0.09
    产品
    0.08
     తయ
    0.08
     manufacturer
    0.08
    Activations Density 0.018%
    No Known Activations