© 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. 11-RESID-POST-AA
    11. 112513
    Prev
    Next
    INDEX
    Explanations

    Romanian language/law

    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
     チ
    -0.09
     kicker
    -0.09
    ڪ
    -0.09
     chase
    -0.09
     ۽
    -0.09
     �
    -0.09
    �
    -0.08
    ڪي
    -0.08
     Chase
    -0.08
     اور
    -0.08
    POSITIVE LOGITS
    ă
    0.10
     Romanian
    0.09
     putea
    0.09
     Romania
    0.08
    -uri
    0.08
     România
    0.08
     magistr
    0.08
     sheds
    0.08
     Bulgar
    0.08
     întâ
    0.08
    Activations Density 0.011%

    No Known Activations