© 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. 63989
    Prev
    Next
    INDEX
    Explanations

    dialogue

    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
     peine
    -0.08
    dum
    -0.07
    ;;;
    -0.07
    .Cart
    -0.07
     tarjetas
    -0.07
    380
    -0.07
     sellele
    -0.07
     eagerly
    -0.07
    :::
    -0.07
     Cleveland
    -0.07
    POSITIVE LOGITS
    怎么办
    0.13
     inesper
    0.11
     situations
    0.10
     ситуа
    0.09
     হলে
    0.09
     aparentemente
    0.09
    вуч
    0.09
    の場合
    0.08
     suspected
    0.08
    Situation
    0.08
    Activations Density 0.124%

    No Known Activations