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. 15-RESID-POST-AA
    6. 19301
    Prev
    Next
    INDEX
    Explanations

    people arranged left/right

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     both
    -0.08
     subset
    -0.08
     two
    -0.08
     subsets
    -0.07
    集
    -0.07
     leverage
    -0.07
    _ZERO
    -0.07
     तकनी
    -0.07
    _TWO
    -0.07
     achats
    -0.07
    POSITIVE LOGITS
    ‍:
    0.10
    :['
    0.10
     σειρά
    0.10
    부터
    0.10
    ):
    0.10
     clockwise
    0.10
    ៖
    0.09
    順
    0.09
    :[↵
    0.09
     հերթ
    0.09
    Activations Density 0.012%

    No Known Activations