© 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. 11-RESID-POST-AA
    11. 31635
    Prev
    Next
    INDEX
    Explanations

    geometry

    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
    Qual
    -0.08
     rollout
    -0.08
    Trim
    -0.08
    nout
    -0.08
     выйти
    -0.07
     climate
    -0.07
    ẹ
    -0.07
    _ret
    -0.07
    vironments
    -0.07
     fron
    -0.07
    POSITIVE LOGITS
     radius
    0.08
    .radius
    0.07
     conducteur
    0.07
     зар
    0.07
     rect
    0.07
     سند
    0.07
     дороги
    0.07
     sup
    0.07
     diámetro
    0.07
     forbidden
    0.07
    Activations Density 0.016%

    No Known Activations