Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 101530
    Prev
    Next
    INDEX
    Explanations

    low impact development

    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
    _special
    -0.08
    _queryset
    -0.07
    Ali
    -0.07
     Lie
    -0.07
    isin
    -0.07
    931
    -0.07
     for
    -0.07
    403
    -0.07
     einn
    -0.07
     특별
    -0.07
    POSITIVE LOGITS
     паспорт
    0.09
    ’ind
    0.09
     madre
    0.08
    Decay
    0.08
     ചര്
    0.08
    ’év
    0.08
     opvang
    0.08
     ltd
    0.08
    TOOLS
    0.08
     coloc
    0.08
    Activations Density 0.009%

    No Known Activations