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. 76536
    Prev
    Next
    INDEX
    Explanations

    Michelin star restaurants

    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
     allowed
    -0.09
     έγινε
    -0.08
    alle
    -0.08
     Mora
    -0.08
     alloys
    -0.07
     Biblical
    -0.07
    -0.07
     Perm
    -0.07
     immun
    -0.07
     chun
    -0.07
    POSITIVE LOGITS
     footsteps
    0.09
    -esque
    0.08
    /navigation
    0.08
    支
    0.08
     prestigious
    0.07
     astr
    0.07
     accolades
    0.07
    -labelled
    0.07
    Locate
    0.07
    。截至
    0.07
    Activations Density 0.002%

    No Known Activations