© 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. 7819
    Prev
    Next
    INDEX
    Explanations

    photographic

    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
     चर्चा
    -0.08
     irr
    -0.08
     "..
    -0.08
     인해
    -0.08
    討
    -0.08
     το
    -0.08
     thôi
    -0.08
     apresentar
    -0.07
     좌
    -0.07
     discussion
    -0.07
    POSITIVE LOGITS
     shotgun
    0.10
     eucalyptus
    0.09
    摄影
    0.08
     shot
    0.08
     Dubai
    0.08
     monoc
    0.08
     Photographer
    0.08
     Shot
    0.08
     Photography
    0.08
     Nowadays
    0.08
    Activations Density 0.008%

    No Known Activations