© 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. 23-RESID-POST-AA
    11. 48462
    Prev
    Next
    INDEX
    Explanations

    say "отив"

    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
    θα
    -0.08
     слив
    -0.08
     hira
    -0.08
     manta
    -0.07
     Aberdeen
    -0.07
     الميل
    -0.07
     Sketch
    -0.07
     河北
    -0.07
    γη
    -0.07
     汉
    -0.07
    POSITIVE LOGITS
    отив
    0.18
    ತ
    0.12
    оти
    0.11
     oposición
    0.10
    ਤੀ
    0.10
    ತಿಯ
    0.10
    તિક
    0.10
    તિ
    0.09
     protiv
    0.09
     қарсы
    0.09
    Activations Density 0.001%

    No Known Activations