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. 11-RESID-POST-AA
    6. 106357
    Prev
    Next
    INDEX
    Explanations

    ление

    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
     举
    -0.08
     kern
    -0.08
     explaining
    -0.08
     duh
    -0.08
     nhằm
    -0.07
    ithmetic
    -0.07
     修
    -0.07
     ज़
    -0.07
    ואל
    -0.07
     z
    -0.07
    POSITIVE LOGITS
     Almost
    0.09
    ynchronous
    0.09
    Almost
    0.08
     వచ్చిన
    0.08
    上映
    0.08
     bijna
    0.08
    Seconds
    0.08
    cook
    0.08
    なが
    0.07
     Solo
    0.07
    Activations Density 0.014%

    No Known Activations