© 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. 19-RESID-POST-AA
    11. 19733
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    циям
    -0.09
    ций
    -0.08
     kõrg
    -0.08
     tšo
    -0.08
     their
    -0.08
    Ự
    -0.08
     processing
    -0.07
     Mersi
    -0.07
    '^
    -0.07
    마사지
    -0.07
    POSITIVE LOGITS
    -threatening
    0.08
     كاملة
    0.08
    wreck
    0.08
    的新
    0.08
    escaping
    0.08
    Endpoints
    0.07
     herpes
    0.07
     النهائي
    0.07
    -vers
    0.07
    侵犯
    0.07
    Activations Density 0.000%

    No Known Activations