© 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. 48102
    Prev
    Next
    INDEX
    Explanations

    у

    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
     Advoc
    -0.08
     autour
    -0.07
     engager
    -0.07
     kinder
    -0.07
     graag
    -0.07
     indice
    -0.07
     తెలుస
    -0.07
     amap
    -0.07
    unque
    -0.07
     അറിയ
    -0.07
    POSITIVE LOGITS
    wię
    0.09
    мира
    0.09
    ================================================================
    0.09
    те
    0.09
    цё
    0.09
    ton
    0.09
    том
    0.09
    ехать
    0.08
    бы
    0.08
    тери
    0.08
    Activations Density 0.002%

    No Known Activations