© 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. 113427
    Prev
    Next
    INDEX
    Explanations

    URL

    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
    kx
    -0.08
     ethos
    -0.07
    Driving
    -0.07
    pct
    -0.07
     khu
    -0.07
     driving
    -0.07
    щу
    -0.07
     soud
    -0.07
     mala
    -0.07
     expect
    -0.07
    POSITIVE LOGITS
    ांकन
    0.09
     rov
    0.09
    =https
    0.08
    entities
    0.08
    elihood
    0.08
    ENTITY
    0.08
    .pathname
    0.08
    .href
    0.08
     Vinc
    0.07
     Ö
    0.07
    Activations Density 0.007%

    No Known Activations