© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 698
    Prev
    Next
    INDEX
    Explanations

    breast

    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
     Dungeon
    -0.08
     Phaser
    -0.08
     Ctrl
    -0.08
     Creature
    -0.08
    Dungeon
    -0.08
     radix
    -0.08
     dinos
    -0.08
     Pray
    -0.07
    Rune
    -0.07
     creature
    -0.07
    POSITIVE LOGITS
     breasts
    0.12
     estrogen
    0.12
     breast
    0.11
     ಮಹಿಳ
    0.11
     మహిళ
    0.11
     women
    0.11
     സ്ത്രീ
    0.11
    女性
    0.11
     महिलाओं
    0.11
     Breast
    0.11
    Activations Density 0.011%

    No Known Activations