Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77179
    Prev
    Next
    INDEX
    Explanations

    ①

    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
     qs
    -0.08
     embry
    -0.08
     acabam
    -0.08
     func
    -0.07
    秦
    -0.07
    ាល
    -0.07
    ]()↵
    -0.07
     Funcion
    -0.07
     режиме
    -0.07
    ែង
    -0.07
    POSITIVE LOGITS
     mellett
    0.08
     lisäksi
    0.08
    और
    0.08
    +i
    0.08
     ઉપરાંત
    0.08
     fair
    0.08
     crib
    0.07
     आणि
    0.07
    нәр
    0.07
    heroes
    0.07
    Activations Density 0.132%

    No Known Activations