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. 12308
    Prev
    Next
    INDEX
    Explanations

    duty

    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
     Boyd
    -0.08
    推
    -0.08
     Cry
    -0.08
    ေလ
    -0.08
     bob
    -0.08
    ώντας
    -0.08
    เอง
    -0.07
     оснащ
    -0.07
    .б
    -0.07
     stimuleren
    -0.07
    POSITIVE LOGITS
     arises
    0.09
    lessness
    0.08
    Exists
    0.08
     vone
    0.08
    Relationship
    0.08
    eless
    0.07
     voyeur
    0.07
     relationship
    0.07
     Realtors
    0.07
    Collectors
    0.07
    Activations Density 0.002%

    No Known Activations