© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1496
    Prev
    Next
    INDEX
    Explanations

    thousands and millions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spi
    -0.09
     remodeled
    -0.09
     metal
    -0.09
     металличес
    -0.09
    sealed
    -0.08
     metalen
    -0.08
     remodeling
    -0.08
     마련
    -0.08
    剤
    -0.08
    -metal
    -0.08
    POSITIVE LOGITS
    点赞
    0.14
     readership
    0.13
     hashtags
    0.12
     hashtag
    0.12
     tweets
    0.11
     millions
    0.10
     ரசிக
    0.10
    hashtags
    0.09
     tweet
    0.09
    投稿
    0.09
    Activations Density 0.047%

    No Known Activations