© 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. 69960
    Prev
    Next
    INDEX
    Explanations

    Colors

    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
     Regiment
    -0.08
     Sno
    -0.08
     sedent
    -0.08
    асс
    -0.08
    motiv
    -0.07
     Zhu
    -0.07
     reh
    -0.07
    ежде
    -0.07
    çisi
    -0.07
     fiercely
    -0.07
    POSITIVE LOGITS
     inks
    0.09
     precip
    0.09
     ppt
    0.08
     reak
    0.08
    -generation
    0.08
     indefinite
    0.08
     gels
    0.08
     gel
    0.08
     flames
    0.08
    変
    0.07
    Activations Density 0.003%

    No Known Activations