© 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. 65479
    Prev
    Next
    INDEX
    Explanations

    npm commands

    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
     તરીકે
    -0.08
     deutsch
    -0.08
     elegance
    -0.08
    غ
    -0.07
    .shape
    -0.07
     diagnóstico
    -0.07
     Wert
    -0.07
    ENDER
    -0.07
    نوع
    -0.07
    =format
    -0.07
    POSITIVE LOGITS
    င်း
    0.08
     bani
    0.08
     �
    0.08
    Common
    0.07
     Common
    0.07
    �
    0.07
     Конститу
    0.07
     teachings
    0.07
     нын
    0.07
     États
    0.07
    Activations Density 0.000%

    No Known Activations