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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19129
    Prev
    Next
    INDEX
    Explanations

    sums and counting

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wzgl
    -0.07
     etc
    -0.07
     forskellige
    -0.07
    čas
    -0.07
     sikker
    -0.07
     Previd
    -0.07
     improvements
    -0.07
     precisam
    -0.07
    stående
    -0.06
     tem
    -0.06
    POSITIVE LOGITS
    (sum
    0.12
     toplam
    0.11
    (total
    0.10
     toplant
    0.10
    (count
    0.09
     કુલ
    0.09
    *num
    0.09
     پنج
    0.09
     büt
    0.09
     Twenty
    0.09
    Activations Density 0.039%

    No Known Activations