© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95181
    Prev
    Next
    INDEX
    Explanations

    lists of keywords

    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
     Ingen
    -0.08
     datang
    -0.08
     campeón
    -0.08
     ach
    -0.08
     elegant
    -0.07
    Wizard
    -0.07
     ukub
    -0.07
     vene
    -0.07
     premiere
    -0.07
     magistr
    -0.07
    POSITIVE LOGITS
    关键词
    0.20
     keywords
    0.20
     Keywords
    0.20
    Keywords
    0.19
    keywords
    0.19
     hashtags
    0.17
    _keywords
    0.17
    (keyword
    0.15
     keyword
    0.15
    hashtags
    0.14
    Activations Density 0.073%

    No Known Activations