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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68542
    Prev
    Next
    INDEX
    Explanations

    mathematical conditions

    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
     SEO
    -0.08
    ’affaire
    -0.08
     Ҳа
    -0.08
    ’affaires
    -0.08
     deeb
    -0.08
     automation
    -0.08
     таҳ
    -0.08
     dee
    -0.08
    готавли
    -0.08
     воқ
    -0.07
    POSITIVE LOGITS
     banning
    0.12
     forb
    0.12
     forbid
    0.12
     prohibits
    0.11
    禁止
    0.11
    Constraint
    0.11
     stric
    0.10
     imposed
    0.09
     Constraint
    0.09
     enforced
    0.09
    Activations Density 0.059%

    No Known Activations