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. 15-RESID-POST-AA
    6. 19211
    Prev
    Next
    INDEX
    Explanations

    say "increase"

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    اثر
    -0.07
     exactly
    -0.07
     equitable
    -0.07
    особ
    -0.07
     profoundly
    -0.07
     ihre
    -0.07
    (dir
    -0.07
     analyser
    -0.07
     populaires
    -0.07
     deeply
    -0.07
    POSITIVE LOGITS
     усл
    0.12
     increasingly
    0.12
     चुनौती
    0.11
     dific
    0.11
     harder
    0.11
     Complexity
    0.11
     progressively
    0.11
     कठिन
    0.11
     progressivement
    0.11
     tougher
    0.10
    Activations Density 0.018%

    No Known Activations