© 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. 23-RESID-POST-AA
    11. 6058
    Prev
    Next
    INDEX
    Explanations

    addiction recovery

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cheats
    -0.08
     adherence
    -0.08
    社会
    -0.08
     fuego
    -0.08
     사회
    -0.08
     koop
    -0.08
     cheating
    -0.08
    .social
    -0.08
     inconsistent
    -0.08
     wap
    -0.08
    POSITIVE LOGITS
     Recovery
    0.11
     recovery
    0.11
     Mutual
    0.11
     Twelve
    0.10
     twelve
    0.10
     AA
    0.10
     SMART
    0.10
     Dual
    0.10
     recovering
    0.09
    Recovery
    0.09
    Activations Density 0.009%

    No Known Activations