© 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. 63446
    Prev
    Next
    INDEX
    Explanations

    mobile text input, keyboards

    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
     Leng
    -0.09
     lengte
    -0.08
    ിച്ചു
    -0.08
     Thin
    -0.08
     Historic
    -0.08
     langleb
    -0.08
     SAB
    -0.08
     sén
    -0.08
    _Runtime
    -0.08
    xeb
    -0.08
    POSITIVE LOGITS
    Fi
    0.09
     terminated
    0.08
     عليهم
    0.07
     treated
    0.07
     communal
    0.07
     classrooms
    0.07
     comunic
    0.07
     colonies
    0.07
     encouraging
    0.07
     infused
    0.07
    Activations Density 0.001%

    No Known Activations