© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 13015
    Prev
    Next
    INDEX
    Explanations

    plan

    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
     ber
    -0.09
     Binnen
    -0.08
     Terry
    -0.08
    掉
    -0.08
     lar
    -0.08
     TRI
    -0.08
    pool
    -0.07
    ع
    -0.07
     folks
    -0.07
     Rookie
    -0.07
    POSITIVE LOGITS
     Tus
    0.10
    inc
    0.09
    Iv
    0.09
    Inc
    0.08
    INC
    0.08
    Tus
    0.08
     infr
    0.08
    仪
    0.08
    截
    0.08
     Inc
    0.08
    Activations Density 0.025%

    No Known Activations