© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30110
    Prev
    Next
    INDEX
    Explanations

    cohesion

    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
     hari
    -0.09
     abaf
    -0.08
     feminine
    -0.08
     Wife
    -0.08
     tane
    -0.08
    Presentation
    -0.07
     bih
    -0.07
     presentation
    -0.07
     waz
    -0.07
     lob
    -0.07
    POSITIVE LOGITS
    -knit
    0.11
     cohesion
    0.10
     xã
    0.10
     solidarity
    0.10
     resilience
    0.10
     solidaridad
    0.09
     solidar
    0.09
     اجتماعی
    0.09
    જૂ
    0.09
     solidarité
    0.09
    Activations Density 0.013%

    No Known Activations