© 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. 29746
    Prev
    Next
    INDEX
    Explanations

    control/mitigation

    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
     worse
    -0.08
    Portrait
    -0.08
    ög
    -0.08
    }{
    -0.07
    Vý
    -0.07
     Kling
    -0.07
    uisse
    -0.07
     итог
    -0.07
     sper
    -0.07
    }↵↵/
    -0.07
    POSITIVE LOGITS
    措施
    0.15
     Maßnahmen
    0.13
     mitigation
    0.12
     उपाय
    0.11
     maatregelen
    0.11
     mitigating
    0.11
     tiltak
    0.11
     اقدامات
    0.11
     നടപട
    0.11
     interventions
    0.10
    Activations Density 0.015%

    No Known Activations