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. 98690
    Prev
    Next
    INDEX
    Explanations

    소

    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
    acar
    -0.09
     Bedeut
    -0.08
    ffee
    -0.08
     గా
    -0.08
     వ్య
    -0.08
    varez
    -0.08
    ILY
    -0.08
     agar
    -0.07
    /her
    -0.07
     হিসেবে
    -0.07
    POSITIVE LOGITS
    聲
    0.09
    声
    0.09
    진
    0.08
    .transpose
    0.08
     quint
    0.07
    زا
    0.07
     momento
    0.07
    ಸ್ತ
    0.07
    شتی
    0.07
    ducers
    0.07
    Activations Density 0.000%

    No Known Activations