© 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. 11-RESID-POST-AA
    11. 110256
    Prev
    Next
    INDEX
    Explanations

    being asked to do something

    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
     AK
    -0.08
     يه
    -0.08
    rip
    -0.07
     ❤️
    -0.07
    woorden
    -0.07
     ;)
    -0.07
     aspiration
    -0.07
     أحمد
    -0.07
     wanna
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    Deliver
    0.09
     schwier
    0.09
     zwing
    0.08
     demanded
    0.08
     reluctantly
    0.08
     complying
    0.08
     ફર
    0.08
    준
    0.08
    ಬೇಕ
    0.08
     કરવાની
    0.08
    Activations Density 0.174%

    No Known Activations