© 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. 13121
    Prev
    Next
    INDEX
    Explanations

    оступ

    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
     Che
    -0.08
    papier
    -0.08
     Virg
    -0.08
     ர
    -0.08
     オ
    -0.07
    콘
    -0.07
     நேர
    -0.07
    upt
    -0.07
     rayon
    -0.07
     நே
    -0.07
    POSITIVE LOGITS
     ca
    0.08
     piercing
    0.07
    (intent
    0.07
    agem
    0.07
     vodka
    0.07
     lieutenant
    0.07
    �
    0.07
    تع
    0.07
     mao
    0.07
     monop
    0.07
    Activations Density 0.001%

    No Known Activations