© 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. 30856
    Prev
    Next
    INDEX
    Explanations

    modeling industry

    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
    bish
    -0.08
     ransomware
    -0.08
     Patriot
    -0.08
     tinnitus
    -0.08
    堡
    -0.08
     Pian
    -0.08
     outages
    -0.08
    ్ట
    -0.08
     Broadband
    -0.08
    兑现
    -0.08
    POSITIVE LOGITS
     photography
    0.10
     Vogue
    0.10
    摄影
    0.10
     photographic
    0.10
    Photography
    0.10
     Photography
    0.10
    写真
    0.09
     lingerie
    0.09
     photographer
    0.09
     photographs
    0.09
    Activations Density 0.044%

    No Known Activations