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. 48657
    Prev
    Next
    INDEX
    Explanations

    east

    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
     Peninsula
    -0.09
     pension
    -0.08
    Thought
    -0.08
    تر
    -0.08
     lid
    -0.08
    елич
    -0.08
    Ct
    -0.07
    福利
    -0.07
     Pension
    -0.07
     Lazar
    -0.07
    POSITIVE LOGITS
     horizontally
    0.09
     horizontal
    0.08
    onclick
    0.08
     phe
    0.08
    .horizontal
    0.08
    horizontal
    0.07
     entrepr
    0.07
     वाहन
    0.07
     carre
    0.07
     মধ্য
    0.07
    Activations Density 0.004%

    No Known Activations