© 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. 2840
    Prev
    Next
    INDEX
    Explanations

    up

    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
     lini
    -0.09
     Dale
    -0.08
     Kai
    -0.07
     Lash
    -0.07
    atorio
    -0.07
     envol
    -0.07
     лини
    -0.07
    kaart
    -0.07
    .timeline
    -0.07
     Bark
    -0.07
    POSITIVE LOGITS
     supplementation
    0.08
    нем
    0.08
    ाशी
    0.07
    翼
    0.07
     resurrection
    0.07
     Ferro
    0.07
     pinnacle
    0.07
     पक
    0.07
    ضاء
    0.07
     Heim
    0.07
    Activations Density 0.079%

    No Known Activations