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. 98198
    Prev
    Next
    INDEX
    Explanations

    os

    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
     salido
    -0.10
     druge
    -0.10
     andere
    -0.10
     hitro
    -0.10
     sobe
    -0.09
     købe
    -0.09
     spise
    -0.09
     andra
    -0.09
     åter
    -0.09
     guste
    -0.09
    POSITIVE LOGITS
    ociazione
    0.12
    iez
    0.11
    aden
    0.11
    uenza
    0.11
    urezza
    0.10
    less
    0.10
    ens
    0.10
    idenza
    0.09
    igen
    0.09
    arian
    0.09
    Activations Density 0.004%

    No Known Activations