© 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. 23-RESID-POST-AA
    11. 49482
    Prev
    Next
    INDEX
    Explanations

    Safety/security

    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
     tweaks
    -0.10
    Suggestions
    -0.10
     suggestion
    -0.10
    Suggestion
    -0.10
    Taste
    -0.09
     suggestions
    -0.09
    Plot
    -0.09
    Packages
    -0.09
     perks
    -0.09
    Team
    -0.09
    POSITIVE LOGITS
    治理
    0.13
    保障
    0.12
     Assurance
    0.12
     assurance
    0.12
     Governance
    0.11
     governance
    0.10
     resilience
    0.10
    安全
    0.10
    可靠
    0.10
     güven
    0.10
    Activations Density 0.076%

    No Known Activations