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. 119420
    Prev
    Next
    INDEX
    Explanations

    Chemical compounds

    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
     enemy
    -0.09
     orth
    -0.08
    Operand
    -0.08
     enemies
    -0.08
    dat
    -0.08
    orth
    -0.08
    xa
    -0.07
    (enemy
    -0.07
    ilevel
    -0.07
    Han
    -0.07
    POSITIVE LOGITS
    !!!
    0.09
     البلا
    0.08
     الاص
    0.08
     tetra
    0.08
     ‎
    0.08
    ۔
    0.08
    -sensitive
    0.07
    آت
    0.07
     sert
    0.07
     چ
    0.07
    Activations Density 0.004%

    No Known Activations