© 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. 18903
    Prev
    Next
    INDEX
    Explanations

    version

    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
     raibh
    -0.09
    राष्ट्रीय
    -0.08
     Bombay
    -0.08
     mitä
    -0.08
     ராஜ
    -0.08
    тий
    -0.08
    America
    -0.08
     americano
    -0.08
     paapaa
    -0.08
     六
    -0.08
    POSITIVE LOGITS
    ="
    0.13
     ="
    0.10
    =\"
    0.10
    =.
    0.10
    =True
    0.09
    =”
    0.09
    ='
    0.09
    =utf
    0.09
    =true
    0.09
    =",
    0.09
    Activations Density 0.000%

    No Known Activations