© 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. 11-RESID-POST-AA
    11. 69422
    Prev
    Next
    INDEX
    Explanations

    reasoning and logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Musée
    -0.08
     Elisabeth
    -0.08
     adgang
    -0.08
    .arch
    -0.07
    .serialization
    -0.07
     Hôtel
    -0.07
     musée
    -0.07
     bonita
    -0.07
     Castillo
    -0.07
     xyz
    -0.07
    POSITIVE LOGITS
     efet
    0.08
     unig
    0.08
    UN
    0.07
     マ
    0.07
    OV
    0.07
    ымды
    0.07
     proportion
    0.07
     percentage
    0.07
    -effect
    0.07
    -
↵
    0.07
    Activations Density 0.002%

    No Known Activations