© 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. 30356
    Prev
    Next
    INDEX
    Explanations

    Self-reference (I/we) in writing

    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
     controll
    -0.07
     suitably
    -0.07
    (or
    -0.07
    至少
    -0.07
    ന്ന
    -0.07
     
    -0.07
     যথ
    -0.07
    Pg
    -0.07
    ಂಟ
    -0.07
    ....
    -0.07
    POSITIVE LOGITS
     Additional
    0.11
     additional
    0.11
     дополнительных
    0.10
     abst
    0.09
    额
    0.09
     lieber
    0.09
     zusätzlichen
    0.09
     aanvullende
    0.09
    additional
    0.08
     disclaim
    0.08
    Activations Density 0.022%

    No Known Activations