© 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. 7875
    Prev
    Next
    INDEX
    Explanations

    formatting citations

    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
    _logits
    -0.09
     empowerment
    -0.09
    .Health
    -0.09
     hunger
    -0.09
     knocked
    -0.08
     reboot
    -0.08
    verbrauch
    -0.08
     xor
    -0.08
     responsiveness
    -0.08
    طرح
    -0.08
    POSITIVE LOGITS
     citation
    0.15
     bibli
    0.14
     APA
    0.13
    格式
    0.13
     MLA
    0.13
     Citation
    0.13
     bibliography
    0.13
     оформить
    0.12
    Citation
    0.12
     format
    0.12
    Activations Density 0.031%

    No Known Activations