© 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. 96752
    Prev
    Next
    INDEX
    Explanations

    المح

    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
     hospitality
    -0.08
    alie
    -0.08
     raids
    -0.08
     cea
    -0.08
    nesty
    -0.08
     giveaway
    -0.07
     inclusion
    -0.07
    purple
    -0.07
    läss
    -0.07
    971
    -0.07
    POSITIVE LOGITS
    رك
    0.16
    ركات
    0.14
    ركة
    0.12
    ريك
    0.11
    .compress
    0.10
    compress
    0.09
     Driving
    0.09
     műkö
    0.09
    Compress
    0.08
     driving
    0.08
    Activations Density 0.001%

    No Known Activations