© 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. 20487
    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
     complexe
    -0.08
     PIN
    -0.08
    IPE
    -0.07
     Pin
    -0.07
     amerikan
    -0.07
    мин
    -0.07
    PIN
    -0.07
     Keith
    -0.07
    ンプ
    -0.07
     processor
    -0.06
    POSITIVE LOGITS
    ૩
    0.10
     երեք
    0.10
     тк
    0.09
     անվտանգության
    0.09
     ट्वी
    0.09
     ukoll
    0.09
     სამი
    0.09
     థ
    0.09
     ткан
    0.09
    ლენ
    0.09
    Activations Density 0.194%

    No Known Activations