© 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. 30212
    Prev
    Next
    INDEX
    Explanations

    online identity

    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
     especiais
    -0.09
     corridor
    -0.08
    icularly
    -0.08
     verlopen
    -0.07
     режим
    -0.07
    മാണ
    -0.07
     especiales
    -0.07
     recém
    -0.07
    roč
    -0.07
     ingest
    -0.07
    POSITIVE LOGITS
    身份
    0.12
     личности
    0.11
     identiteit
    0.11
     anonymity
    0.11
     identité
    0.10
     anonymous
    0.10
    'ident
    0.10
     identidade
    0.10
    匿名
    0.10
    anonymous
    0.10
    Activations Density 0.053%

    No Known Activations