© 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. 19-RESID-POST-AA
    11. 102673
    Prev
    Next
    INDEX
    Explanations

    negative outcomes

    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
    erings
    -0.08
     Dövlət
    -0.08
    atures
    -0.08
    ygons
    -0.08
    isans
    -0.08
    ಂಗಳ
    -0.08
     Een
    -0.08
    -Based
    -0.08
     Société
    -0.08
    ynomials
    -0.08
    POSITIVE LOGITS
     complications
    0.10
     downtime
    0.10
     expenses
    0.10
     complexity
    0.10
     hassles
    0.09
     difficulties
    0.09
     hassle
    0.09
     complication
    0.09
     discomfort
    0.09
     annoyance
    0.09
    Activations Density 0.012%

    No Known Activations