© 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. 19-RESID-POST-AA
    11. 18785
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abrupt
    -0.08
    ++,
    -0.07
     sudden
    -0.07
    lod
    -0.07
    ASE
    -0.07
    었다
    -0.07
     tõttu
    -0.07
    ्ने
    -0.07
     ruz
    -0.07
     隆
    -0.07
    POSITIVE LOGITS
    -between
    0.10
     אחרי
    0.10
     بين
    0.09
     below
    0.09
     BELOW
    0.09
     berada
    0.09
     beneath
    0.09
     outside
    0.09
     debajo
    0.09
     বাইরে
    0.09
    Activations Density 0.015%

    No Known Activations