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. 55990
    Prev
    Next
    INDEX
    Explanations

    Lists

    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
     kn
    -0.09
    த
    -0.08
     netjes
    -0.08
     tov
    -0.07
     Lek
    -0.07
    ಿಯಿಂದ
    -0.07
     censorship
    -0.07
    Lek
    -0.07
    遮
    -0.07
    madan
    -0.07
    POSITIVE LOGITS
    尤其
    0.12
     richest
    0.11
    иболее
    0.10
     особенно
    0.10
     gebieden
    0.10
     strongest
    0.10
     Besonders
    0.10
     particulièrement
    0.09
     наиболее
    0.09
     regions
    0.09
    Activations Density 0.113%

    No Known Activations