© 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. 63474
    Prev
    Next
    INDEX
    Explanations

    stunned

    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
     بر
    -0.08
     Won
    -0.08
     ضمن
    -0.08
     ذلك
    -0.08
     بن
    -0.07
     بنا
    -0.07
     طرح
    -0.07
    Won
    -0.07
    [this
    -0.07
    embang
    -0.07
    POSITIVE LOGITS
    और
    0.10
    /Data
    0.10
    _and
    0.09
    _AND
    0.09
     আৰু
    0.09
     nor
    0.09
     və
    0.09
    ＆
    0.09
     và
    0.09
     Và
    0.09
    Activations Density 1.110%

    No Known Activations