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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 54086
    Prev
    Next
    INDEX
    Explanations

    Cross-linking

    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
     inclin
    -0.08
     carg
    -0.08
     dove
    -0.08
     còn
    -0.08
     Euros
    -0.08
     announcing
    -0.07
     relinqu
    -0.07
     rarity
    -0.07
     pě
    -0.07
     larga
    -0.07
    POSITIVE LOGITS
     chemically
    0.09
     bonds
    0.08
    _STRUCT
    0.08
     zorgt
    0.08
    _bind
    0.08
    -binding
    0.08
    剤
    0.08
     sigma
    0.08
     raakt
    0.08
     formed
    0.08
    Activations Density 0.002%

    No Known Activations