© 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. 71218
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     del
    -0.07
    Chan
    -0.07
    Agents
    -0.07
    Thr
    -0.07
     primera
    -0.07
    okay
    -0.07
    ilie
    -0.07
     Thr
    -0.07
    .ag
    -0.07
    Shield
    -0.06
    POSITIVE LOGITS
    (sorted
    0.09
    sorted
    0.09
    _sorted
    0.09
     contradiction
    0.09
     Contrary
    0.09
    逆
    0.08
    ▲
    0.08
     Sorted
    0.08
     sorted
    0.08
     contradict
    0.08
    Activations Density 0.030%

    No Known Activations