© 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. 7894
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    gelegen
    -0.09
     attained
    -0.08
     ಆ
    -0.07
    เด
    -0.07
     Proxy
    -0.07
     زمانی
    -0.07
     временем
    -0.07
     کړئ
    -0.07
     अवस्थ
    -0.07
     وقت
    -0.07
    POSITIVE LOGITS
     contributes
    0.12
     contribute
    0.10
     contribue
    0.09
     bijdrage
    0.09
     pile
    0.09
    处理中
    0.09
     dég
    0.08
     gout
    0.08
     contribut
    0.08
     contribution
    0.08
    Activations Density 0.039%

    No Known Activations