© 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. 11-RESID-POST-AA
    11. 7709
    Prev
    Next
    INDEX
    Explanations

    delete files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dignity
    -0.08
    xtəlif
    -0.08
    '%
    -0.08
    tok
    -0.08
     maggiore
    -0.08
     امکان
    -0.08
     قابلیت
    -0.07
    /token
    -0.07
     dimainkan
    -0.07
     został
    -0.07
    POSITIVE LOGITS
    artos
    0.09
     ruthless
    0.08
    .minus
    0.08
     drastic
    0.08
     negative
    0.08
     negatieve
    0.08
     Negative
    0.08
    erton
    0.08
    Deletes
    0.07
     Herce
    0.07
    Activations Density 0.003%

    No Known Activations