© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47874
    Prev
    Next
    INDEX
    Explanations

    ware

    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
     Alger
    -0.08
    伤
    -0.08
     speeches
    -0.08
    اربة
    -0.08
     germs
    -0.08
     noexcept
    -0.08
     transcend
    -0.08
     dealers
    -0.08
    isse
    -0.08
    eners
    -0.08
    POSITIVE LOGITS
     Adobe
    0.08
     Fate
    0.08
    萬
    0.07
    _into
    0.07
     finesse
    0.07
     Hum
    0.07
    _fin
    0.07
     Happiness
    0.07
     Macintosh
    0.07
    .netty
    0.07
    Activations Density 0.002%

    No Known Activations