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. 98479
    Prev
    Next
    INDEX
    Explanations

    Adoption and breeding

    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
     analy
    -0.09
     γρα
    -0.09
    'analyse
    -0.08
     machining
    -0.08
    煤
    -0.08
     groove
    -0.08
     분석
    -0.08
    分析
    -0.08
     bevel
    -0.08
     двигатель
    -0.08
    POSITIVE LOGITS
     adoption
    0.27
     Adoption
    0.27
     breeding
    0.25
     adop
    0.25
     adopter
    0.24
     adopté
    0.24
     kennel
    0.24
    养
    0.24
     captivity
    0.23
     adopt
    0.23
    Activations Density 0.100%

    No Known Activations