© 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. 95668
    Prev
    Next
    INDEX
    Explanations

    Citrus fruits

    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
     enlist
    -0.08
     podstaw
    -0.08
     slavery
    -0.08
    ena
    -0.08
    ledger
    -0.08
     enemies
    -0.08
     Kol
    -0.07
     enact
    -0.07
     ਹੋ
    -0.07
     particulares
    -0.07
    POSITIVE LOGITS
     citrus
    0.10
     grapefruit
    0.10
     xan
    0.09
     Citrus
    0.09
     cleanser
    0.08
     trif
    0.08
     güne
    0.08
     promo
    0.08
     Greeting
    0.08
     fragrances
    0.08
    Activations Density 0.007%

    No Known Activations