© 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. 110407
    Prev
    Next
    INDEX
    Explanations

    reflection

    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
     Ninja
    -0.08
     Walter
    -0.08
     iniciativas
    -0.07
     지속
    -0.07
     stringent
    -0.07
    .criteria
    -0.07
     initiatives
    -0.07
    /events
    -0.07
    .states
    -0.07
     удоб
    -0.07
    POSITIVE LOGITS
    _Construct
    0.10
     sprang
    0.08
    绕
    0.08
    _ELEMENT
    0.08
     monoch
    0.08
     skall
    0.08
    _Y
    0.08
     spiegel
    0.08
    还
    0.08
     qiym
    0.08
    Activations Density 0.009%

    No Known Activations