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. 45500
    Prev
    Next
    INDEX
    Explanations

    Core abdominal muscles

    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
     피
    -0.09
    	EXPECT
    -0.08
    áid
    -0.08
     зл
    -0.08
    	points
    -0.08
    	expect
    -0.08
    .Foreground
    -0.07
    내용
    -0.07
    .Expect
    -0.07
     altogether
    -0.07
    POSITIVE LOGITS
    াচ
    0.07
     ಸಂಕ
    0.07
     !
    0.07
    69
    0.07
     kwambiri
    0.07
     গভ
    0.07
    ıç
    0.07
     கொண்ட
    0.07
    ুখ
    0.07
    .types
    0.07
    Activations Density 0.002%

    No Known Activations