© 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. 6136
    Prev
    Next
    INDEX
    Explanations

    feline viruses

    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
     Teller
    -0.08
    erne
    -0.08
    T
    -0.07
     crazy
    -0.07
    >T
    -0.07
    ્યાન
    -0.07
     appointed
    -0.07
    PE
    -0.07
     Yun
    -0.07
    otation
    -0.07
    POSITIVE LOGITS
    ベント
    0.08
     ishl
    0.08
     blender
    0.08
     پرې
    0.08
     wedge
    0.07
    ەم
    0.07
     خروج
    0.07
     لن
    0.07
    ด้
    0.07
     kleurr
    0.07
    Activations Density 0.001%

    No Known Activations