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. 77569
    Prev
    Next
    INDEX
    Explanations

    +

    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
     maquina
    -0.08
     Rory
    -0.07
    compile
    -0.07
     yen
    -0.07
     lit
    -0.07
     nickel
    -0.07
    yos
    -0.07
    -link
    -0.07
     Yen
    -0.07
     marg
    -0.07
    POSITIVE LOGITS
    直到
    0.11
     countless
    0.09
    など
    0.08
    등
    0.08
     εί
    0.08
    越来越
    0.08
     indefinitely
    0.08
    čka
    0.08
     usw
    0.08
     आदि
    0.08
    Activations Density 0.041%

    No Known Activations