© 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. 103412
    Prev
    Next
    INDEX
    Explanations

    vice

    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
    ized
    -0.11
    IZED
    -0.11
    IZES
    -0.10
    izasyon
    -0.09
    isation
    -0.09
    IZATION
    -0.09
    ization
    -0.09
    ised
    -0.08
    isme
    -0.08
    ize
    -0.08
    POSITIVE LOGITS
    -president
    0.21
    -President
    0.19
    -prés
    0.17
    -presidente
    0.16
     President
    0.15
    -chief
    0.15
     president
    0.15
    -министр
    0.14
     പ്രസിഡന്റ്
    0.14
    President
    0.14
    Activations Density 0.009%

    No Known Activations