© 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. 49285
    Prev
    Next
    INDEX
    Explanations

    say "words ending with 'ola', 'olo', or 'ole'"

    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
     MX
    -0.07
     namespace
    -0.07
    EV
    -0.07
    MX
    -0.07
     qry
    -0.07
    CTA
    -0.07
     MAY
    -0.07
    565
    -0.07
     adaptability
    -0.07
     hugging
    -0.07
    POSITIVE LOGITS
    ole
    0.09
    oler
    0.08
    olarmente
    0.08
    coni
    0.08
    оле
    0.08
    оло
    0.07
    ريق
    0.07
     pitcher
    0.07
    صيد
    0.07
    احونة
    0.07
    Activations Density 0.000%

    No Known Activations