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. 53148
    Prev
    Next
    INDEX
    Explanations

    or

    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
    尺寸
    -0.08
     eder
    -0.08
     especializados
    -0.07
     bezig
    -0.07
    trizes
    -0.07
     размеры
    -0.07
     அள
    -0.07
    .font
    -0.07
     специализирован
    -0.07
     desider
    -0.07
    POSITIVE LOGITS
     Unexpected
    0.11
    Unexpected
    0.10
     mastermind
    0.10
     überras
    0.10
     shocking
    0.10
     inesper
    0.09
     onverw
    0.09
     thriller
    0.09
     неож
    0.09
     finale
    0.09
    Activations Density 0.017%

    No Known Activations