© 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. 113348
    Prev
    Next
    INDEX
    Explanations

    Geography and climate

    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
     cheaper
    -0.09
     expensive
    -0.09
     は
    -0.08
    pem
    -0.08
     vidéos
    -0.08
     randomly
    -0.08
     financially
    -0.07
    视频网站
    -0.07
     particulièrement
    -0.07
    рей
    -0.07
    POSITIVE LOGITS
     northeastern
    0.09
     northeast
    0.08
    般
    0.08
    杜
    0.08
    �
    0.08
    าะ
    0.08
     practicality
    0.07
    妹
    0.07
    범
    0.07
     صنا
    0.07
    Activations Density 0.012%

    No Known Activations