© 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. 113585
    Prev
    Next
    INDEX
    Explanations

    vectors and geometry

    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
     Españ
    -0.08
     WO
    -0.08
     fierc
    -0.08
     soundtrack
    -0.08
     AR
    -0.07
     Ar
    -0.07
     MM
    -0.07
     Opinions
    -0.07
     whenever
    -0.07
    _MM
    -0.07
    POSITIVE LOGITS
    .destination
    0.10
     конце
    0.10
    Destination
    0.10
    まで
    0.10
    destination
    0.10
     Destination
    0.09
     النهائي
    0.09
     destination
    0.09
     వరకు
    0.09
     окончания
    0.09
    Activations Density 0.047%

    No Known Activations