© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-RESID-POST-AA
    11. 16346
    Prev
    Next
    INDEX
    Explanations

    Sending messages

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Intersection
    -0.08
     fertile
    -0.08
     intersections
    -0.08
     oči
    -0.07
     reopened
    -0.07
     Cuts
    -0.07
     scop
    -0.07
     incont
    -0.07
    이에
    -0.07
     detective
    -0.07
    POSITIVE LOGITS
    发送
    0.22
     भेज
    0.22
     મોક
    0.19
    Sending
    0.19
     ارسال
    0.19
     gönder
    0.19
     sending
    0.18
     gönd
    0.18
     إرسال
    0.18
     envoyer
    0.18
    Activations Density 0.026%

    No Known Activations