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. 90560
    Prev
    Next
    INDEX
    Explanations

    balls

    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
     tere
    -0.09
    Preco
    -0.09
    ilate
    -0.08
     tert
    -0.08
     yollar
    -0.08
     preco
    -0.08
     seconda
    -0.08
     inhale
    -0.08
     awaken
    -0.08
     risch
    -0.08
    POSITIVE LOGITS
    	init
    0.08
    CRM
    0.08
    �
    0.08
     dunk
    0.07
    SSH
    0.07
     SSH
    0.07
     extermin
    0.07
     biscuits
    0.07
    	default
    0.07
     बन
    0.07
    Activations Density 0.006%

    No Known Activations