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. 53356
    Prev
    Next
    INDEX
    Explanations

    EPR paradox

    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
     infected
    -0.08
     הקד
    -0.07
    platform
    -0.07
     Каб
    -0.07
     precious
    -0.07
    .platform
    -0.07
     automatically
    -0.07
    (platform
    -0.07
     mulch
    -0.07
     Plataforma
    -0.07
    POSITIVE LOGITS
     filóso
    0.09
    ъяв
    0.08
    acam
    0.08
     philosoph
    0.08
     প্রত্য
    0.08
     uncanny
    0.08
     αρχ
    0.08
     выб
    0.08
     campo
    0.08
    oretical
    0.07
    Activations Density 0.000%

    No Known Activations