© 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. 19-RESID-POST-AA
    11. 102429
    Prev
    Next
    INDEX
    Explanations

    conditional logic

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     measurements
    -0.09
     jumlah
    -0.08
     différences
    -0.08
     budgets
    -0.08
     supermarkets
    -0.08
     scores
    -0.08
     മത്സര
    -0.08
     경쟁
    -0.08
     competed
    -0.08
     battling
    -0.08
    POSITIVE LOGITS
    "If
    0.21
     conditional
    0.21
    conditional
    0.19
    “If
    0.19
    Conditional
    0.19
     Conditional
    0.18
     implication
    0.18
     logic
    0.16
     theorem
    0.15
     implications
    0.15
    Activations Density 0.088%

    No Known Activations