© 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. 110612
    Prev
    Next
    INDEX
    Explanations

    seeks

    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
    rif
    -0.08
    Detached
    -0.08
    ూల
    -0.08
     Wis
    -0.07
    。因此
    -0.07
     raz
    -0.07
    utm
    -0.07
     --↵↵
    -0.07
    Central
    -0.07
    Education
    -0.07
    POSITIVE LOGITS
     déput
    0.09
     nuevamente
    0.09
    agnetic
    0.08
     yine
    0.08
    pegno
    0.08
    urve
    0.08
     incl
    0.07
    报道称
    0.07
     유명
    0.07
     опять
    0.07
    Activations Density 0.862%

    No Known Activations