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. 65699
    Prev
    Next
    INDEX
    Explanations

    glue or unifying forces

    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
     contribution
    -0.08
     dama
    -0.07
     extravagant
    -0.07
    ('');↵↵
    -0.07
    206
    -0.07
     prognosis
    -0.07
     kih
    -0.07
     contingent
    -0.07
     berichten
    -0.07
     Contribution
    -0.07
    POSITIVE LOGITS
     glue
    0.11
     connective
    0.10
    butikk
    0.09
     connecting
    0.09
     בין
    0.09
     cohesion
    0.09
     mellom
    0.08
     bağ
    0.08
    aluronic
    0.08
    连接
    0.08
    Activations Density 0.017%

    No Known Activations