Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 106227
    Prev
    Next
    INDEX
    Explanations

    Connection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     €
    -0.09
    crypt
    -0.09
    財布
    -0.09
     (€
    -0.09
    crypted
    -0.08
     ransom
    -0.08
    uuid
    -0.08
     provocative
    -0.08
    É
    -0.08
    raz
    -0.08
    POSITIVE LOGITS
     Callback
    0.11
     Tabla
    0.10
     callback
    0.09
     XMLHttp
    0.09
     callbacks
    0.08
     xhr
    0.08
    Callback
    0.08
     Tabelle
    0.08
     Dre
    0.08
     Inline
    0.08
    Activations Density 0.002%

    No Known Activations