© 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. 19-RESID-POST-AA
    11. 20109
    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
    вая
    -0.09
    ऊ
    -0.09
    אַפּ
    -0.09
    ვამ
    -0.09
    ऊन
    -0.09
    गी
    -0.08
    ვის
    -0.08
    bauen
    -0.08
    აწ
    -0.08
    выя
    -0.08
    POSITIVE LOGITS
    antro
    0.10
    acter
    0.09
    atoren
    0.09
    inkan
    0.09
    istic
    0.09
     Christi
    0.08
    ostics
    0.08
    one
    0.08
    enschap
    0.08
    ísticas
    0.08
    Activations Density 0.001%

    No Known Activations