© 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. 65038
    Prev
    Next
    INDEX
    Explanations

    solution sets in math

    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
    'univers
    -0.08
     multe
    -0.08
    ’univers
    -0.08
    	comment
    -0.08
        ↵    ↵    ↵
    -0.07
    למיד
    -0.07
    	res
    -0.07
    realm
    -0.07
     realm
    -0.07
    ```
    -0.07
    POSITIVE LOGITS
    Either
    0.09
     supposed
    0.09
     either
    0.08
    omething
    0.08
     supposedly
    0.08
     Either
    0.08
    ittää
    0.08
     possível
    0.08
    ಿತರ
    0.07
    සු
    0.07
    Activations Density 0.167%

    No Known Activations