© 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. 3-RESID-POST-AA
    11. 13393
    Prev
    Next
    INDEX
    Explanations

    playlist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cradle
    -0.08
     penis
    -0.08
     �
    -0.08
     בג
    -0.08
     Pflanzen
    -0.07
    升
    -0.07
     alumin
    -0.07
     glands
    -0.07
     Abl
    -0.07
     अंग
    -0.07
    POSITIVE LOGITS
     curated
    0.08
     मालिक
    0.08
    赖
    0.07
    ей
    0.07
     mutant
    0.07
     wellness
    0.07
    ông
    0.07
     Galaxy
    0.07
     ming
    0.07
    ïc
    0.07
    Activations Density 0.003%

    No Known Activations