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. 106189
    Prev
    Next
    INDEX
    Explanations

    prime numbers and factorization

    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
     kokku
    -0.09
     briefs
    -0.09
    .lifecycle
    -0.08
    工资
    -0.08
    国务院
    -0.08
    类别
    -0.08
     veo
    -0.08
    /button
    -0.08
     dore
    -0.08
     vena
    -0.08
    POSITIVE LOGITS
    _candidate
    0.09
    _Is
    0.08
     is
    0.08
     लाग
    0.08
     candidate
    0.08
     పరీక్ష
    0.08
     એટલે
    0.07
     candidates
    0.07
     అంటే
    0.07
     صحة
    0.07
    Activations Density 0.010%

    No Known Activations