© 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. 11-RESID-POST-AA
    11. 30906
    Prev
    Next
    INDEX
    Explanations

    Rules and conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     literal
    -0.08
    陈
    -0.08
    无需
    -0.08
    -exclusive
    -0.07
     पण
    -0.07
     literals
    -0.07
     literally
    -0.07
    Li
    -0.07
    Mario
    -0.07
    -minute
    -0.07
    POSITIVE LOGITS
     тщ
    0.13
     тщательно
    0.13
     sorgfält
    0.13
     Carefully
    0.13
     soigne
    0.12
     carefully
    0.12
     careful
    0.12
     осторож
    0.11
     cuidadosamente
    0.11
     caution
    0.10
    Activations Density 0.090%

    No Known Activations