© 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. 108122
    Prev
    Next
    INDEX
    Explanations

    exercise

    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
     tweets
    -0.08
    peech
    -0.08
     להתמודד
    -0.07
     supremacy
    -0.07
     overlays
    -0.07
    ZS
    -0.07
     Spurs
    -0.07
     Parts
    -0.07
     companions
    -0.07
     companion
    -0.07
    POSITIVE LOGITS
     itr
    0.09
     aerobic
    0.09
     praz
    0.09
     умер
    0.09
    EOF
    0.09
     calmly
    0.09
     gentle
    0.08
     enquiry
    0.08
     intenso
    0.08
     doucement
    0.08
    Activations Density 0.009%

    No Known Activations