© 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. 7-RESID-POST-AA
    11. 1025
    Prev
    Next
    INDEX
    Explanations

    H

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moro
    -0.08
     gente
    -0.08
     Libert
    -0.08
     faire
    -0.08
     लोक
    -0.07
     दूस
    -0.07
     Nay
    -0.07
     inconvenience
    -0.07
     लोगों
    -0.07
     Gentle
    -0.07
    POSITIVE LOGITS
     Wordpress
    0.08
    鱼
    0.08
    �
    0.08
    duino
    0.08
     lix
    0.08
     hun
    0.07
    炉
    0.07
    Geek
    0.07
     Minimal
    0.07
    睛
    0.07
    Activations Density 0.010%

    No Known Activations