© 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. 113307
    Prev
    Next
    INDEX
    Explanations

    sibling

    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
     Aga
    -0.09
     constitucional
    -0.09
     mobili
    -0.09
     rectangular
    -0.08
     Jung
    -0.08
    angt
    -0.08
     gait
    -0.08
     Parlamento
    -0.08
     largos
    -0.08
     larga
    -0.08
    POSITIVE LOGITS
    Food
    0.08
    _FLASH
    0.08
    Pric
    0.08
    Named
    0.08
    失
    0.08
    _food
    0.07
    -food
    0.07
    _CHILD
    0.07
     Food
    0.07
    _N
    0.07
    Activations Density 0.032%

    No Known Activations