© 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. 1009
    Prev
    Next
    INDEX
    Explanations

    Assyrian

    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
     Lexus
    -0.08
     lancer
    -0.08
    .sep
    -0.08
     plank
    -0.07
     مالک
    -0.07
    Maj
    -0.07
     владель
    -0.07
     Porter
    -0.07
    ਿਰ
    -0.07
     donated
    -0.07
    POSITIVE LOGITS
     infant
    0.09
     Infant
    0.09
     Une
    0.08
    gal
    0.08
     MER
    0.08
     Hotel
    0.08
     heterogeneous
    0.08
     infants
    0.08
     mill
    0.08
    Sandbox
    0.08
    Activations Density 0.043%

    No Known Activations