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. 97957
    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
    FFFFFF
    -0.16
    FFFFFFFF
    -0.14
    ffffff
    -0.12
    581
    -0.10
     Manuel
    -0.09
    ۰۰
    -0.09
    621
    -0.09
    FFFF
    -0.09
    .WHITE
    -0.09
    iquement
    -0.09
    POSITIVE LOGITS
    ccc
    0.14
    ddd
    0.14
    bbb
    0.13
    acc
    0.12
    ccd
    0.12
    aaa
    0.12
    aac
    0.12
    bbc
    0.12
    abc
    0.12
    bcc
    0.11
    Activations Density 0.004%

    No Known Activations