© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69012
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     identification
    -0.07
    	editor
    -0.07
     ermöglicht
    -0.07
    。从
    -0.07
    用于
    -0.07
     estate
    -0.07
     nearest
    -0.07
    -sur
    -0.07
    _iso
    -0.07
    owych
    -0.06
    POSITIVE LOGITS
     долго
    0.10
     sabes
    0.09
     کچھ
    0.09
     awaited
    0.09
     uninterrupted
    0.09
     flawlessly
    0.09
     شکست
    0.08
     kotlinx
    0.08
     interrom
    0.08
     غلط
    0.08
    Activations Density 0.022%

    No Known Activations