© 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 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. 63970
    Prev
    Next
    INDEX
    Explanations

    90s numbers

    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
     mating
    -0.08
    �
    -0.07
     GK
    -0.07
     chanc
    -0.07
     coping
    -0.07
     settling
    -0.07
    birth
    -0.06
     EK
    -0.06
     residency
    -0.06
    _detect
    -0.06
    POSITIVE LOGITS
     الاقتصادية
    0.08
     рублей
    0.08
    едом
    0.08
    [label
    0.08
    chio
    0.07
    Wanted
    0.07
     Rah
    0.07
     اقتص
    0.07
     Hundreds
    0.07
    睛
    0.07
    Activations Density 0.122%

    No Known Activations