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. 76732
    Prev
    Next
    INDEX
    Explanations

    protect

    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
     मक
    -0.08
    	user
    -0.08
     user
    -0.08
     shaking
    -0.08
    ">(
    -0.07
     laying
    -0.07
    (question
    -0.07
     Question
    -0.07
     사용자
    -0.07
    ?>
    -0.07
    POSITIVE LOGITS
     Catar
    0.08
     chit
    0.08
     catar
    0.08
     pertes
    0.08
     тос
    0.08
     mes
    0.08
     pels
    0.07
     Elast
    0.07
    ��
    0.07
     emergencies
    0.07
    Activations Density 0.010%

    No Known Activations