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. 45943
    Prev
    Next
    INDEX
    Explanations

    ing

    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
     perseverance
    -0.08
     volatile
    -0.08
    лава
    -0.08
    482
    -0.07
    .advance
    -0.07
    毅
    -0.07
     الموضوع
    -0.07
     conhecer
    -0.07
    事
    -0.07
     dimensão
    -0.07
    POSITIVE LOGITS
     siente
    0.08
    icating
    0.08
     ఛ
    0.07
    umatic
    0.07
    epo
    0.07
     आपल्या
    0.07
    (sel
    0.07
    ibel
    0.07
    /th
    0.07
    yme
    0.07
    Activations Density 0.002%

    No Known Activations