© 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. 3-RESID-POST-AA
    11. 1038
    Prev
    Next
    INDEX
    Explanations

    ичный

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     venit
    -0.08
     cds
    -0.07
    นั้น
    -0.07
    masa
    -0.07
     బాల
    -0.07
     biased
    -0.07
     Astra
    -0.07
     BH
    -0.07
     CSA
    -0.07
     duel
    -0.07
    POSITIVE LOGITS
     Businesses
    0.08
     আর
    0.08
    串
    0.08
    ieb
    0.07
     जाग
    0.07
    flat
    0.07
     Fixture
    0.07
    its
    0.07
    දී
    0.07
     businesses
    0.07
    Activations Density 0.002%

    No Known Activations