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. 45281
    Prev
    Next
    INDEX
    Explanations

    <

    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
     patrol
    -0.09
    이터
    -0.09
     FBI
    -0.09
     judiciary
    -0.08
     preseason
    -0.08
    udoku
    -0.08
     vortex
    -0.08
     Patrol
    -0.08
     வீர
    -0.08
     Quiz
    -0.08
    POSITIVE LOGITS
    .maven
    0.13
     Maven
    0.12
    .xml
    0.11
     xmlns
    0.10
     scm
    0.10
    xmlns
    0.10
     npm
    0.09
     xsi
    0.09
     jars
    0.09
    .package
    0.09
    Activations Density 0.008%

    No Known Activations