© 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. 111246
    Prev
    Next
    INDEX
    Explanations

    |

    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
     desperation
    -0.08
    亿美元
    -0.08
     zusätzlich
    -0.08
    旦
    -0.08
    .shtml
    -0.07
    typen
    -0.07
    -0.07
     gefragt
    -0.07
     یافت
    -0.07
     popping
    -0.07
    POSITIVE LOGITS
     Subject
    0.09
     LOT
    0.08
    ीय
    0.08
     Latest
    0.07
     Counts
    0.07
    heen
    0.07
     counts
    0.07
     итог
    0.07
    pert
    0.07
    ીક
    0.07
    Activations Density 0.017%
    No Known Activations