© 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. 11-RESID-POST-AA
    6. 68491
    Prev
    Next
    INDEX
    Explanations

    reach

    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
     Wesley
    -0.08
     verdens
    -0.08
     Lel
    -0.07
     denom
    -0.07
     satisfactor
    -0.07
    час
    -0.07
     permis
    -0.07
     Dragon
    -0.07
     renomm
    -0.07
    Und
    -0.07
    POSITIVE LOGITS
     확대
    0.09
     बढ़
    0.09
     강화
    0.09
     বাড়
    0.08
     측
    0.08
     વધ
    0.08
     cooker
    0.08
     Imperial
    0.08
     �
    0.07
    担当
    0.07
    Activations Density 0.006%

    No Known Activations