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. 112765
    Prev
    Next
    INDEX
    Explanations

    Napoleon

    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
    Encoding
    -0.08
    (vertical
    -0.08
    Subdivision
    -0.08
     holes
    -0.08
    /send
    -0.08
     hole
    -0.08
    coment
    -0.08
     aguj
    -0.08
    part
    -0.08
    Hole
    -0.08
    POSITIVE LOGITS
     invade
    0.10
     Napoleon
    0.09
     ly
    0.09
     Otto
    0.09
     Constantine
    0.09
     troops
    0.09
     REF
    0.09
     Defender
    0.09
     germany
    0.08
     RAND
    0.08
    Activations Density 0.006%

    No Known Activations