Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130737
    Prev
    Next
    INDEX
    Explanations

    Треб/реб

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     становятся
    -0.10
    _ATTRIBUTES
    -0.09
    ുകയായിരുന്നു
    -0.08
     stays
    -0.08
     libc
    -0.08
    _LIB
    -0.08
     represented
    -0.07
     dargestellt
    -0.07
     übernommen
    -0.07
    анием
    -0.07
    POSITIVE LOGITS
    ует
    0.14
    уется
    0.14
    уют
    0.10
    уются
    0.09
    S
    0.08
     vien
    0.08
    ования
    0.08
     понадобится
    0.08
    须
    0.08
    уй
    0.08
    Activations Density 0.003%

    No Known Activations