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. 45151
    Prev
    Next
    INDEX
    Explanations

    statistical matching/analysis

    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
     undis
    -0.08
     wob
    -0.08
    ITIES
    -0.08
    CIÓN
    -0.08
    țional
    -0.07
    ូល
    -0.07
     финанс
    -0.07
    agnes
    -0.07
    LIC
    -0.07
    WAYS
    -0.07
    POSITIVE LOGITS
     Prototype
    0.08
    	cv
    0.08
    	unit
    0.07
    	code
    0.07
     creat
    0.07
    ールド
    0.07
     tutoring
    0.07
     নির্ম
    0.07
    合同
    0.07
    });↵↵
    0.07
    Activations Density 0.001%

    No Known Activations