© 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. 31289
    Prev
    Next
    INDEX
    Explanations

    Controversial articles/posts

    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
     LF
    -0.08
    ด
    -0.08
    omat
    -0.08
     abwechslungs
    -0.08
    �
    -0.07
    reter
    -0.07
    sy
    -0.07
     comprimento
    -0.07
     yz
    -0.07
    ändig
    -0.07
    POSITIVE LOGITS
     alleged
    0.15
     allegedly
    0.14
     purported
    0.14
     supposedly
    0.14
     controversy
    0.13
     controversial
    0.13
     accused
    0.13
    涉嫌
    0.12
     controvers
    0.12
     debated
    0.12
    Activations Density 0.314%

    No Known Activations