© 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. 68435
    Prev
    Next
    INDEX
    Explanations

    acker

    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
     sanitation
    -0.09
    留言
    -0.08
    验
    -0.08
    保証
    -0.08
     viet
    -0.08
    验证
    -0.08
     immobilier
    -0.08
     petition
    -0.07
    筹
    -0.07
     tabletop
    -0.07
    POSITIVE LOGITS
     Jackets
    0.08
    خور
    0.08
    aceous
    0.08
    tun
    0.07
    øn
    0.07
    دوز
    0.07
     intenso
    0.07
    wake
    0.07
     NATO
    0.07
     SNS
    0.07
    Activations Density 0.004%

    No Known Activations