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. 29956
    Prev
    Next
    INDEX
    Explanations

    mid

    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
     aner
    -0.08
     etwa
    -0.08
     amus
    -0.08
     Emerald
    -0.08
     irregular
    -0.08
    -active
    -0.08
     monop
    -0.08
     Emerg
    -0.07
     précise
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     guy
    0.09
     dude
    0.08
     رجل
    0.07
    ibo
    0.07
    izo
    0.07
     polarity
    0.07
     आदमी
    0.07
     Guy
    0.07
     fucking
    0.07
     достоин
    0.07
    Activations Density 0.003%

    No Known Activations