© 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. 22056
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    merking
    -0.08
    âmica
    -0.08
     पहिलो
    -0.07
    以下简称
    -0.07
    ámica
    -0.07
     yaiku
    -0.07
    .capitalize
    -0.07
    ښه
    -0.07
    amique
    -0.07
     umuntu
    -0.07
    POSITIVE LOGITS
     numerous
    0.36
     العديد
    0.33
     countless
    0.33
     множество
    0.33
     many
    0.32
     multitude
    0.32
     अनेक
    0.32
     zahlreiche
    0.31
     많은
    0.31
     nombreuses
    0.31
    Activations Density 0.130%

    No Known Activations