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. 76884
    Prev
    Next
    INDEX
    Explanations

    only / que

    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
    Chest
    -0.08
    ename
    -0.08
    (car
    -0.08
     मात्र
    -0.07
    irmware
    -0.07
    	B
    -0.07
    اث
    -0.07
    가지
    -0.07
     calme
    -0.07
    	headers
    -0.07
    POSITIVE LOGITS
     centr
    0.10
     exclusivement
    0.08
     ceux
    0.07
    )");↵
    0.07
    বোৰ
    0.07
     stric
    0.07
    SELECT
    0.07
     aquellas
    0.07
    、更
    0.07
    浆
    0.07
    Activations Density 0.041%

    No Known Activations