© 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. 30213
    Prev
    Next
    INDEX
    Explanations

    .uk

    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
    .There
    -0.09
     okus
    -0.08
     Award
    -0.08
     Order
    -0.08
    Ako
    -0.08
     reconna
    -0.08
     towels
    -0.08
     ocen
    -0.08
     Encoding
    -0.08
     Initi
    -0.08
    POSITIVE LOGITS
    꾸
    0.08
     hatch
    0.08
     nucle
    0.07
    haus
    0.07
     permanence
    0.07
     vier
    0.07
    	sub
    0.07
     parameter
    0.07
     hadd
    0.07
     jum
    0.07
    Activations Density 0.001%

    No Known Activations