© 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. 1218
    Prev
    Next
    INDEX
    Explanations

    )

    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
     кра
    -0.08
     Holm
    -0.07
    That's
    -0.07
     moves
    -0.07
    уляр
    -0.07
     sker
    -0.07
     Blanket
    -0.07
    <p
    -0.07
     mountain
    -0.07
     bouquet
    -0.07
    POSITIVE LOGITS
    141
    0.09
     shiny
    0.08
    -bearing
    0.08
     synerg
    0.08
    agno
    0.08
     circulation
    0.07
    兵
    0.07
     eti
    0.07
    ്യേ
    0.07
     Semi
    0.07
    Activations Density 0.035%

    No Known Activations