© 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 EvalsExportsinterp-engineNEWAPI 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. 50875
    Prev
    Next
    INDEX
    Explanations

    lightning

    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
     doucement
    -0.08
     dilution
    -0.08
    .Push
    -0.08
    uers
    -0.08
    lcool
    -0.07
    iş
    -0.07
     Push
    -0.07
     Sahib
    -0.07
     Digest
    -0.07
    engin
    -0.07
    POSITIVE LOGITS
     lightning
    0.25
     बिजली
    0.24
     Lightning
    0.22
    Lightning
    0.21
     thunderstorms
    0.20
     bolts
    0.20
     electricity
    0.20
     thunder
    0.19
    雷
    0.19
     bolt
    0.19
    Activations Density 0.044%

    No Known Activations