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. 44000
    Prev
    Next
    INDEX
    Explanations

    journal article citations

    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
     уб
    -0.09
     være
    -0.08
     seinen
    -0.08
    \M
    -0.08
    TL
    -0.08
     Betracht
    -0.07
     Trick
    -0.07
     phosphory
    -0.07
    ์
    -0.07
     Leuten
    -0.07
    POSITIVE LOGITS
    107
    0.08
    102
    0.08
    business
    0.08
    605
    0.08
    棒
    0.08
     sabotage
    0.07
    desk
    0.07
    908
    0.07
     abras
    0.07
    603
    0.07
    Activations Density 0.005%

    No Known Activations