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. 7-RESID-POST-AA
    6. 131006
    Prev
    Next
    INDEX
    Explanations

    polenta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obo
    -0.08
    adres
    -0.08
     конце
    -0.08
    .PR
    -0.08
    agli
    -0.08
    abla
    -0.07
    email
    -0.07
     dovol
    -0.07
    iseau
    -0.07
    .(
    -0.07
    POSITIVE LOGITS
     satisfacer
    0.08
     따
    0.08
     tanta
    0.07
     geschiedenis
    0.07
     matemática
    0.07
     equations
    0.07
     Wal
    0.07
    -history
    0.07
     salió
    0.07
     conversar
    0.07
    Activations Density 0.000%

    No Known Activations