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. 45194
    Prev
    Next
    INDEX
    Explanations

    5

    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
    fc
    -0.08
    trusted
    -0.08
     promoted
    -0.07
    >-->↵
    -0.07
    �
    -0.07
    uller
    -0.07
     Cm
    -0.07
     (...)↵↵
    -0.07
    avn
    -0.07
     seperate
    -0.07
    POSITIVE LOGITS
    "In
    0.08
     descriptions
    0.08
     deluxe
    0.08
    描述
    0.08
    ,即
    0.08
     vivid
    0.08
     locom
    0.07
    זה
    0.07
    "T
    0.07
    	es
    0.07
    Activations Density 0.006%

    No Known Activations