© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29387
    Prev
    Next
    INDEX
    Explanations

    geometry shapes

    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
     bcrypt
    -0.09
     overse
    -0.08
    Uz
    -0.08
     ambientes
    -0.08
     ADN
    -0.08
    PIN
    -0.08
     PIN
    -0.07
     पर्य
    -0.07
    ोन
    -0.07
    stitial
    -0.07
    POSITIVE LOGITS
     Behind
    0.10
     espetáculo
    0.09
    Behind
    0.09
     silhou
    0.09
    Hollywood
    0.09
     photographed
    0.09
    _visible
    0.09
     Cameras
    0.08
    opaque
    0.08
     behind
    0.08
    Activations Density 0.021%

    No Known Activations