© 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. 111171
    Prev
    Next
    INDEX
    Explanations

    Raising something

    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
     supplemented
    -0.09
     provision
    -0.08
     Websites
    -0.08
    -being
    -0.08
    _sites
    -0.07
    Sites
    -0.07
    ilus
    -0.07
    Built
    -0.07
     Supplement
    -0.07
     supplement
    -0.07
    POSITIVE LOGITS
     уст
    0.08
     eins
    0.08
     глаза
    0.08
    manı
    0.08
    窗
    0.08
     applause
    0.08
     глаз
    0.08
     corps
    0.08
     vantage
    0.08
    يدي
    0.08
    Activations Density 0.007%

    No Known Activations