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. 11-RESID-POST-AA
    6. 43688
    Prev
    Next
    INDEX
    Explanations

    Bowl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Back
    -0.08
     indire
    -0.07
    gericht
    -0.07
    جي
    -0.07
    Congress
    -0.07
     waarschijnlijk
    -0.07
     Congress
    -0.07
    جو
    -0.07
    ج
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    —all
    0.13
    等等
    0.12
     lastly
    0.11
     વગેરે
    0.11
     എന്നിവ
    0.10
     enfim
    0.09
     आदि
    0.09
     Whatever
    0.09
     */}↵↵
    0.09
     usw
    0.08
    Activations Density 0.225%

    No Known Activations