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. 111706
    Prev
    Next
    INDEX
    Explanations

    speed

    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
     outsider
    -0.08
    itable
    -0.08
    ordable
    -0.08
    仁
    -0.08
     Auß
    -0.08
    _ROUT
    -0.08
    fillable
    -0.08
    agnar
    -0.08
     voire
    -0.07
     classiques
    -0.07
    POSITIVE LOGITS
     converted
    0.11
     expressed
    0.11
    mill
    0.10
    converted
    0.10
     meters
    0.10
     mill
    0.09
     باللغة
    0.09
     represented
    0.09
    Converted
    0.08
     Mill
    0.08
    Activations Density 0.084%

    No Known Activations