Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60977
    Prev
    Next
    INDEX
    Explanations

    Buy

    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
     Continue
    -0.08
     evenly
    -0.08
     hunters
    -0.08
     தொக
    -0.07
     össze
    -0.07
     conquer
    -0.07
     évoluer
    -0.07
     вза
    -0.07
    数组
    -0.07
     Final
    -0.07
    POSITIVE LOGITS
    rare
    0.08
    richting
    0.08
    ging
    0.08
    	ll
    0.08
    	private
    0.08
     rare
    0.08
    	timeout
    0.07
    receipt
    0.07
     rol
    0.07
     occ
    0.07
    Activations Density 0.002%

    No Known Activations