© 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. 19-RESID-POST-AA
    11. 103342
    Prev
    Next
    INDEX
    Explanations

    healthy/safe

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     негатив
    -0.14
     плох
    -0.14
     negatieve
    -0.14
     kötü
    -0.13
     detrimental
    -0.13
     negativ
    -0.12
     незакон
    -0.12
     negative
    -0.12
     schlechte
    -0.12
     incompat
    -0.12
    POSITIVE LOGITS
     healthy
    0.20
    正常
    0.19
     benign
    0.19
     정상
    0.18
     safe
    0.18
    healthy
    0.18
     intact
    0.17
    safe
    0.17
     unaffected
    0.17
     wholesome
    0.16
    Activations Density 0.131%

    No Known Activations