© 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 EvalsExportsAPI 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. 69480
    Prev
    Next
    INDEX
    Explanations

    {

    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
     coun
    -0.08
     Prov
    -0.08
     provocative
    -0.08
     mortar
    -0.08
    够
    -0.08
    �
    -0.08
     prov
    -0.07
     sidoo
    -0.07
    迫
    -0.07
     همچنین
    -0.07
    POSITIVE LOGITS
    주는
    0.09
    vg
    0.08
     किए
    0.07
    uba
    0.07
    ે
    0.07
     Herstell
    0.07
    VO
    0.07
    ிக்கப்பட்ட
    0.07
     गर्दा
    0.07
    plist
    0.07
    Activations Density 0.003%

    No Known Activations