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. 43409
    Prev
    Next
    INDEX
    Explanations

    electric

    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
     bakin
    -0.08
     فيه
    -0.08
     मिलता
    -0.07
    afir
    -0.07
    skih
    -0.07
     defe
    -0.07
     smo
    -0.07
     nasil
    -0.07
     shorten
    -0.07
     fro
    -0.07
    POSITIVE LOGITS
     propulsion
    0.08
     Volt
    0.08
    -powered
    0.08
    玩
    0.08
     потреб
    0.08
    �
    0.07
    益
    0.07
     broadband
    0.07
    响
    0.07
     Sy
    0.07
    Activations Density 0.007%

    No Known Activations