Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88315
    Prev
    Next
    INDEX
    Explanations

    body parts

    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
     Relationships
    -0.09
    Relationships
    -0.09
     wines
    -0.09
     relationships
    -0.08
     Beziehungen
    -0.08
     juices
    -0.08
    :,
    -0.08
     zut
    -0.08
    Ai
    -0.08
     Wines
    -0.08
    POSITIVE LOGITS
     protección
    0.11
     shields
    0.11
     protection
    0.10
     couvr
    0.10
     Shield
    0.10
     proteção
    0.10
    shield
    0.10
     shield
    0.10
    Shield
    0.09
     protections
    0.09
    Activations Density 0.022%

    No Known Activations