© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51072
    Prev
    Next
    INDEX
    Explanations

    кара

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    desa
    -0.09
     distract
    -0.08
    lex
    -0.08
    onavirus
    -0.08
    logged
    -0.07
     mahu
    -0.07
     সংখ্য
    -0.07
     hlub
    -0.07
     Baru
    -0.07
     Wishlist
    -0.07
    POSITIVE LOGITS
    оке
    0.10
    okes
    0.10
    oke
    0.10
    зін
    0.09
    OKE
    0.09
    ોકે
    0.09
    okee
    0.08
    �
    0.08
    ктер
    0.08
    KEN
    0.07
    Activations Density 0.002%

    No Known Activations