© 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. 19-RESID-POST-AA
    11. 22346
    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
     오전
    -0.08
    ،↵
    -0.08
    ੍ਹ
    -0.08
    Afee
    -0.08
     오후
    -0.08
     afternoons
    -0.08
    ੀਂ
    -0.08
    -upper
    -0.08
    ың
    -0.08
    'âge
    -0.08
    POSITIVE LOGITS
     different
    0.12
     variations
    0.12
     diferentes
    0.12
    Different
    0.12
     multiple
    0.11
     разные
    0.11
     variation
    0.11
     разных
    0.10
     forskellige
    0.10
     generic
    0.10
    Activations Density 0.010%

    No Known Activations