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. 54194
    Prev
    Next
    INDEX
    Explanations

    Seasoning food inside

    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
    (initial
    -0.08
     mistakenly
    -0.08
     initially
    -0.08
    마트
    -0.08
     irrespons
    -0.08
     اشت
    -0.08
     whichever
    -0.08
    וסט
    -0.07
    是多少
    -0.07
    ertain
    -0.07
    POSITIVE LOGITS
     Desc
    0.08
     ceremon
    0.08
     decorations
    0.08
    desc
    0.08
     天津
    0.08
     ചടങ്ങ
    0.08
     descending
    0.08
     personalization
    0.07
    äumen
    0.07
    Desc
    0.07
    Activations Density 0.006%

    No Known Activations