Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1670
    Prev
    Next
    INDEX
    Explanations

    already

    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
     Xen
    -0.09
     প্রব
    -0.08
     Lund
    -0.08
     Eins
    -0.07
     rising
    -0.07
     trif
    -0.07
    关闭
    -0.07
    576
    -0.07
    Polit
    -0.07
     turpis
    -0.07
    POSITIVE LOGITS
    Blo
    0.08
    盆
    0.08
    ìn
    0.08
     rur
    0.08
     Wanda
    0.08
    藏
    0.08
    棒
    0.08
     Blo
    0.07
     Hampshire
    0.07
    hasa
    0.07
    Activations Density 0.014%

    No Known Activations