© 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. 69870
    Prev
    Next
    INDEX
    Explanations

    cold showers

    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
     rubric
    -0.08
     acad
    -0.08
     Revision
    -0.07
     revision
    -0.07
     rii
    -0.07
     reads
    -0.07
     fiduci
    -0.07
     Reed
    -0.07
     syllabus
    -0.07
     எழுத
    -0.07
    POSITIVE LOGITS
     sauna
    0.11
     सुख
    0.10
     Sauna
    0.10
     immersive
    0.09
     ketosis
    0.09
     immers
    0.09
     inhal
    0.09
     angenehm
    0.09
     atmospheric
    0.09
     invigor
    0.09
    Activations Density 0.005%

    No Known Activations