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. 131046
    Prev
    Next
    INDEX
    Explanations

    **

    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
    ,同时
    -0.11
     jedoch
    -0.10
     utilizing
    -0.10
    。同时
    -0.10
     helaas
    -0.10
    :"↵
    -0.10
     sadly
    -0.09
     Cependant
    -0.09
     unfortunately
    -0.09
     malheureusement
    -0.09
    POSITIVE LOGITS
    It
    0.14
     It
    0.13
    The
    0.12
    They
    0.12
    Rain
    0.12
     seventeen
    0.12
    There
    0.12
     eighteen
    0.11
     മഴ
    0.11
     thirteen
    0.11
    Activations Density 0.051%

    No Known Activations