© 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. 23-RESID-POST-AA
    11. 5369
    Prev
    Next
    INDEX
    Explanations

    AI automation

    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
     somewhat
    -0.10
     বেশ
    -0.09
     nogle
    -0.09
     einiger
    -0.09
     কিছু
    -0.09
     bazı
    -0.08
     khá
    -0.08
     stos
    -0.08
    %^
    -0.08
    认真
    -0.08
    POSITIVE LOGITS
     automáticamente
    0.18
     automatiquement
    0.18
     automaticamente
    0.18
     personalized
    0.17
     automatisch
    0.17
     instantly
    0.17
     dynamically
    0.16
     AI
    0.16
     automatically
    0.15
    AI
    0.15
    Activations Density 0.119%

    No Known Activations