© 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. 111257
    Prev
    Next
    INDEX
    Explanations

    tool

    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
    485
    -0.08
    odes
    -0.08
     Tom
    -0.07
    蝶
    -0.07
    089
    -0.07
     Overs
    -0.07
     ICD
    -0.07
    露
    -0.07
     Georg
    -0.07
     concom
    -0.07
    POSITIVE LOGITS
    kits
    0.10
    tips
    0.09
     Bolsa
    0.08
    /li
    0.08
    เหล
    0.07
     bantu
    0.07
    /editor
    0.07
    smöglichkeiten
    0.07
     burdens
    0.07
    快捷
    0.07
    Activations Density 0.023%

    No Known Activations