© 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. 3-RESID-POST-AA
    11. 1374
    Prev
    Next
    INDEX
    Explanations

    opt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trực
    -0.10
     tận
    -0.08
     Gau
    -0.08
     принят
    -0.07
    ewu
    -0.07
     quyết
    -0.07
    782
    -0.07
    ilib
    -0.07
    hao
    -0.07
    ্যে
    -0.07
    POSITIVE LOGITS
    axes
    0.07
     Zar
    0.07
     circumvent
    0.07
    �
    0.07
    LEN
    0.07
    ARC
    0.07
     friction
    0.07
     ME
    0.07
     Sturm
    0.06
     LEN
    0.06
    Activations Density 0.002%

    No Known Activations