© 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. 23-RESID-POST-AA
    11. 96231
    Prev
    Next
    INDEX
    Explanations

    say "the ending -tered"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENS
    -0.09
     Congresso
    -0.09
    137
    -0.09
    138
    -0.09
     COS
    -0.09
    ggy
    -0.09
    liwo
    -0.08
     đóng
    -0.08
    139
    -0.08
    ZG
    -0.08
    POSITIVE LOGITS
     сказал
    0.10
     ಹೇಳ
    0.09
     म्ह
    0.09
    说道
    0.09
     sorti
    0.09
     сказать
    0.08
     отметил
    0.08
     zegt
    0.08
     कहा
    0.08
     сказала
    0.08
    Activations Density 0.001%

    No Known Activations