© 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. 23-RESID-POST-AA
    11. 51026
    Prev
    Next
    INDEX
    Explanations

    Security-related 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
     europeos
    -0.09
     собрать
    -0.08
     convaincre
    -0.08
     Coalition
    -0.08
     teaming
    -0.08
    .uni
    -0.07
    Exports
    -0.07
     вт
    -0.07
    conv
    -0.07
     européens
    -0.07
    POSITIVE LOGITS
     Sicherheits
    0.15
     Security
    0.14
     sécurité
    0.14
     Seguridad
    0.13
     security
    0.13
     Interior
    0.13
     Sicherheit
    0.13
     bezpe
    0.13
     सुरक्षा
    0.13
     segurança
    0.13
    Activations Density 0.014%

    No Known Activations