© 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. 26292
    Prev
    Next
    INDEX
    Explanations

    cow

    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
     �
    -0.08
    dop
    -0.08
     سف
    -0.07
     curly
    -0.07
     centrifugal
    -0.07
     neur
    -0.07
    fi
    -0.07
    മുള്ള
    -0.07
    dal
    -0.07
    เป
    -0.06
    POSITIVE LOGITS
     Fab
    0.10
    Shade
    0.09
     moo
    0.08
     Zhang
    0.08
     марки
    0.08
    Fab
    0.08
     Shade
    0.08
    women
    0.08
    yard
    0.08
     slaughter
    0.08
    Activations Density 0.013%

    No Known Activations