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. 12736
    Prev
    Next
    INDEX
    Explanations

    prepositions/articles

    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
    iktok
    -0.09
     Outro
    -0.09
     serio
    -0.08
    	sf
    -0.08
     Español
    -0.08
     Incluso
    -0.08
    Garant
    -0.08
     bedacht
    -0.07
    농
    -0.07
    Outro
    -0.07
    POSITIVE LOGITS
    0.07
     islam
    0.07
    (Path
    0.07
    יס
    0.07
    侯
    0.07
    ερ
    0.07
    真正
    0.07
    (collection
    0.07
     hai
    0.07
     δημο
    0.07
    Activations Density 0.669%

    No Known Activations