© 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. 23-RESID-POST-AA
    11. 49673
    Prev
    Next
    INDEX
    Explanations

    GERD and acid reflux

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     кишеч
    -0.09
    _Int
    -0.08
    艇
    -0.08
     intestine
    -0.08
     handeln
    -0.07
    enton
    -0.07
     vervo
    -0.07
     çiz
    -0.07
    ựa
    -0.07
    Thomas
    -0.07
    POSITIVE LOGITS
     reflux
    0.17
     GER
    0.15
     es
    0.15
     acid
    0.13
     hiatus
    0.13
     LES
    0.13
     hi
    0.13
     ulcers
    0.13
     refl
    0.13
     gastr
    0.12
    Activations Density 0.017%

    No Known Activations