© 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. 23-RESID-POST-AA
    11. 49015
    Prev
    Next
    INDEX
    Explanations

    Arithmetic

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inuu
    -0.09
    Shi
    -0.08
     спортив
    -0.08
    .ws
    -0.08
     résoudre
    -0.08
     Martí
    -0.08
     Shi
    -0.08
    drawable
    -0.08
    cel
    -0.08
     yaşay
    -0.07
    POSITIVE LOGITS
    Adobe
    0.08
     Adobe
    0.08
    ilia
    0.08
     નહ
    0.07
     ailments
    0.07
     unseren
    0.07
     meinen
    0.07
     ail
    0.07
    abric
    0.07
     Digitalisierung
    0.07
    Activations Density 0.020%

    No Known Activations