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. 67783
    Prev
    Next
    INDEX
    Explanations

    Argumentative text

    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
     বাজ
    -0.07
     regio
    -0.07
    ジェ
    -0.07
     verwend
    -0.07
     departed
    -0.07
    دې
    -0.07
     πα
    -0.07
    漂
    -0.07
     ミ
    -0.07
    .energy
    -0.07
    POSITIVE LOGITS
     pourtant
    0.12
     nor
    0.08
     nuance
    0.08
     seriously
    0.08
     nuances
    0.08
     actually
    0.08
     nuanced
    0.08
     faktiskt
    0.08
     реально
    0.08
     제대로
    0.08
    Activations Density 0.269%

    No Known Activations