© 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. 3-RESID-POST-AA
    11. 1336
    Prev
    Next
    INDEX
    Explanations

    Fantasy worldbuilding systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cona
    -0.08
    挂
    -0.08
    截图
    -0.08
    快捷
    -0.07
     Convenience
    -0.07
    Alexa
    -0.07
     Kitchen
    -0.07
     قرارداد
    -0.07
    Kitchen
    -0.07
    von
    -0.07
    POSITIVE LOGITS
     fiction
    0.08
    (wallet
    0.07
    .OR
    0.07
    ウォ
    0.07
    ESO
    0.07
     immigration
    0.07
    owitz
    0.07
     Holocaust
    0.07
     industri
    0.07
     perpetual
    0.07
    Activations Density 0.255%

    No Known Activations