© 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. 102247
    Prev
    Next
    INDEX
    Explanations

    you

    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
     Cuando
    -0.08
     denke
    -0.08
    ө
    -0.08
     دا
    -0.08
    Congrats
    -0.08
     creo
    -0.08
    thing
    -0.08
     pense
    -0.08
     penso
    -0.08
     Pense
    -0.08
    POSITIVE LOGITS
     qualidade
    0.12
     rate
    0.12
    .rate
    0.12
    质量
    0.12
    -rate
    0.11
    -quality
    0.11
     गुणवत्ता
    0.11
     quality
    0.11
     RATE
    0.10
     calidad
    0.10
    Activations Density 0.000%

    No Known Activations