© 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. 11-RESID-POST-AA
    11. 63214
    Prev
    Next
    INDEX
    Explanations

    visual

    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
    prav
    -0.08
     Sprach
    -0.08
     jemand
    -0.08
    δή
    -0.08
     Call
    -0.07
     Signal
    -0.07
    -Ray
    -0.07
     salute
    -0.07
     Rett
    -0.07
     Tog
    -0.07
    POSITIVE LOGITS
    ，因此
    0.15
    ，所以
    0.13
     ולכן
    0.13
    ，而
    0.12
     поэтому
    0.12
    ですが
    0.11
    ，但
    0.11
     ويمكن
    0.11
     dlatego
    0.10
    ，但是
    0.10
    Activations Density 0.388%

    No Known Activations