© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 109795
    Prev
    Next
    INDEX
    Explanations

    vertical orientation

    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
    Negative Logits
     Clearing
    -0.08
    edo
    -0.08
     ?>">
    -0.07
     czyn
    -0.07
     актив
    -0.07
     Rett
    -0.07
    kommens
    -0.07
    ativ
    -0.07
     zem
    -0.07
    ibang
    -0.07
    POSITIVE LOGITS
    Few
    0.07
    र्प
    0.07
    Phrase
    0.07
    alph
    0.07
     infección
    0.07
    -virus
    0.07
    స్ట్
    0.07
     قطر
    0.07
     Jug
    0.07
     kump
    0.07
    Activations Density 0.006%

    No Known Activations