© 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 EvalsExportsinterp-engineNEWAPI 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. 110494
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
    pickle
    -0.08
    Theta
    -0.08
     అవ
    -0.08
    ёз
    -0.08
    foreach
    -0.08
    Prest
    -0.07
    છ
    -0.07
    cle
    -0.07
    Est
    -0.07
    por
    -0.07
    POSITIVE LOGITS
     lads
    0.08
    —or
    0.08
     wap
    0.08
    ിന്ന
    0.08
    ↵ ↵
    0.08
     بالح
    0.08
    ർമ
    0.07
    ിലേക്ക്
    0.07
     학
    0.07
     produceren
    0.07
    Activations Density 0.126%

    No Known Activations