© 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. 19151
    Prev
    Next
    INDEX
    Explanations

    international

    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
    enced
    -0.10
    /or
    -0.09
    IEF
    -0.09
     from
    -0.09
    ibili
    -0.08
    itive
    -0.08
     each
    -0.08
    ief
    -0.08
    ied
    -0.08
    encing
    -0.08
    POSITIVE LOGITS
     cooperación
    0.10
     cooperation
    0.10
     협
    0.10
     colaboração
    0.10
     colaborar
    0.10
    合作
    0.09
     voisins
    0.09
     solidaridad
    0.09
     solidarity
    0.09
     prostor
    0.09
    Activations Density 0.006%

    No Known Activations