© 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. 31529
    Prev
    Next
    INDEX
    Explanations

    statue

    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
     Emails
    -0.09
     juices
    -0.09
     emails
    -0.08
    Emails
    -0.08
    emails
    -0.08
     pantry
    -0.08
     Intensive
    -0.08
     certeza
    -0.08
    adecimal
    -0.08
     unglaublich
    -0.08
    POSITIVE LOGITS
     sculptures
    0.18
     statue
    0.15
     sculpture
    0.14
     monuments
    0.13
     украш
    0.13
     statues
    0.13
     commemor
    0.13
    雕
    0.13
     monument
    0.12
     escult
    0.12
    Activations Density 0.029%

    No Known Activations