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. 97988
    Prev
    Next
    INDEX
    Explanations

    say the ending -iding

    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
    astic
    -0.08
    mediate
    -0.08
    іч
    -0.08
    on
    -0.08
     medi
    -0.07
    itur
    -0.07
     servi
    -0.07
    onar
    -0.07
    ested
    -0.07
    iciar
    -0.07
    POSITIVE LOGITS
    iding
    0.20
    ided
    0.17
    idingen
    0.13
    iders
    0.13
    idings
    0.13
    ids
    0.12
    ider
    0.11
    IDS
    0.11
    idding
    0.10
    idable
    0.10
    Activations Density 0.001%

    No Known Activations