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. 130974
    Prev
    Next
    INDEX
    Explanations

    say "ors"

    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
     ụ
    -0.10
    çadas
    -0.09
    mig
    -0.09
    mik
    -0.09
    zeda
    -0.09
    resolution
    -0.08
    ூர
    -0.08
    zad
    -0.08
    assment
    -0.08
    therapy
    -0.08
    POSITIVE LOGITS
    ors
    0.18
    ibility
    0.12
     divis
    0.12
    ators
    0.11
    ORS
    0.10
    encers
    0.10
    itors
    0.10
    orship
    0.10
    orial
    0.09
    ifiers
    0.09
    Activations Density 0.006%

    No Known Activations