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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98131
    Prev
    Next
    INDEX
    Explanations

    أغ

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toj
    -0.09
     DVR
    -0.07
    שו
    -0.07
    ico
    -0.07
    ట
    -0.07
     EV
    -0.07
    angan
    -0.07
    sof
    -0.07
     VIC
    -0.07
    ג
    -0.07
    POSITIVE LOGITS
    mier
    0.08
    ്യേ
    0.08
    coding
    0.07
    ename
    0.07
     Weak
    0.07
    لبية
    0.07
     بالر
    0.07
    Coding
    0.07
     dada
    0.07
    يب
    0.07
    Activations Density 0.001%

    No Known Activations