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. 98250
    Prev
    Next
    INDEX
    Explanations

    File extensions and formats

    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
     retourne
    -0.09
    тернат
    -0.08
     amafaranga
    -0.08
     retourn
    -0.08
     retourner
    -0.08
    ғын
    -0.08
     monnaie
    -0.08
    ственным
    -0.08
    šan
    -0.08
     πρω
    -0.08
    POSITIVE LOGITS
     N
    0.09
    N
    0.08
    D
    0.08
    nf
    0.08
    calls
    0.08
    Calls
    0.08
     wil
    0.07
    olidays
    0.07
    ija
    0.07
    ost
    0.07
    Activations Density 0.000%

    No Known Activations