© 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. 95214
    Prev
    Next
    INDEX
    Explanations

    word of the day

    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
     spite
    -0.08
     увер
    -0.08
     mergers
    -0.08
     বাঁ
    -0.08
    _squared
    -0.07
     несмотря
    -0.07
     Għ
    -0.07
     divor
    -0.07
     detached
    -0.07
     penile
    -0.07
    POSITIVE LOGITS
    毎
    0.15
    마다
    0.14
     semanal
    0.14
     сайын
    0.13
    weekly
    0.12
     diariamente
    0.12
    daily
    0.12
     Weekly
    0.12
     weekly
    0.12
    每日
    0.11
    Activations Density 0.096%

    No Known Activations