© 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. 96355
    Prev
    Next
    INDEX
    Explanations

    losing something

    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
    ئلة
    -0.09
    _failure
    -0.08
     olemas
    -0.08
    错误
    -0.08
    ailure
    -0.08
    _error
    -0.08
     réussite
    -0.07
     victoria
    -0.07
     Ergeb
    -0.07
    ופות
    -0.07
    POSITIVE LOGITS
     السيطرة
    0.16
     sight
    0.15
     touch
    0.15
     grip
    0.14
     footing
    0.13
     track
    0.13
     contacto
    0.13
     aansluiting
    0.12
     traction
    0.12
     contrôle
    0.12
    Activations Density 0.046%

    No Known Activations