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. 29810
    Prev
    Next
    INDEX
    Explanations

    language

    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
    sets
    -0.08
    mo
    -0.08
    _spaces
    -0.08
    marketing
    -0.08
    _custom
    -0.07
    -0.07
    _ad
    -0.07
    _replace
    -0.07
    Mo
    -0.07
    WHAT
    -0.07
    POSITIVE LOGITS
     танҳо
    0.09
     idioma
    0.09
     langue
    0.09
    -language
    0.09
     limitation
    0.09
     Gelukkig
    0.09
     scholar
    0.08
     тоқ
    0.08
    ��
    0.08
     researcher
    0.08
    Activations Density 0.004%

    No Known Activations