© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 49147
    Prev
    Next
    INDEX
    Explanations

    legal terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    磁
    -0.12
     магнит
    -0.11
     magnets
    -0.11
     magnetic
    -0.11
     magnet
    -0.11
    Temperature
    -0.11
     Fitbit
    -0.11
     Magnetic
    -0.10
     smoothie
    -0.10
     Ryzen
    -0.10
    POSITIVE LOGITS
    法律
    0.57
     legal
    0.53
     சட்ட
    0.51
     juridische
    0.50
    Legal
    0.50
     Legal
    0.49
     আইন
    0.48
     القانونية
    0.48
     юрид
    0.47
     juridique
    0.47
    Activations Density 0.236%

    No Known Activations