© 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. 18697
    Prev
    Next
    INDEX
    Explanations

    :

    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
     installed
    -0.08
    	unsigned
    -0.08
     unsigned
    -0.08
     in
    -0.08
     predicted
    -0.07
     ни
    -0.07
    unsigned
    -0.07
     лам
    -0.07
     incont
    -0.07
     uner
    -0.07
    POSITIVE LOGITS
     ratios
    0.10
     ratio
    0.10
    JOR
    0.09
     hieman
    0.09
     تقری
    0.09
    .COL
    0.09
    �
    0.09
     Ratio
    0.09
     yleensä
    0.09
     meestal
    0.09
    Activations Density 0.002%

    No Known Activations