© 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. 8121
    Prev
    Next
    INDEX
    Explanations

    Broad generalizations and imprecision

    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
    FEATURE
    -0.08
    Stories
    -0.08
     Hik
    -0.08
    徽
    -0.08
    stories
    -0.07
    Peek
    -0.07
     inspire
    -0.07
    νο
    -0.07
     اک
    -0.07
    Copyright
    -0.07
    POSITIVE LOGITS
     indis
    0.18
     blanket
    0.13
     wholesale
    0.11
     crude
    0.10
     массов
    0.10
     broadly
    0.10
     широкий
    0.09
     broad
    0.09
     breadth
    0.09
     crud
    0.09
    Activations Density 0.064%

    No Known Activations