© 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. 24850
    Prev
    Next
    INDEX
    Explanations

    construction activities/remediation

    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
     perks
    -0.10
     Spotlight
    -0.10
    消费
    -0.09
    emoji
    -0.09
     geek
    -0.09
     caffe
    -0.09
     nerd
    -0.09
     indie
    -0.09
     😉
    -0.09
     creators
    -0.09
    POSITIVE LOGITS
    施工
    0.15
     grout
    0.12
     vegetation
    0.12
     asphalt
    0.11
     сооруж
    0.10
     towing
    0.10
    Removal
    0.10
    Temporary
    0.10
     remediation
    0.10
     грун
    0.09
    Activations Density 0.048%

    No Known Activations