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. 77453
    Prev
    Next
    INDEX
    Explanations

    Tableau

    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
     pomen
    -0.08
     divul
    -0.07
     considers
    -0.07
    .Crypt
    -0.07
    går
    -0.07
     Pun
    -0.07
    oking
    -0.07
    ishna
    -0.07
     Israel
    -0.07
     Decl
    -0.07
    POSITIVE LOGITS
     realitat
    0.08
     �
    0.08
     कस
    0.08
     mobility
    0.07
     زیب
    0.07
     turístico
    0.07
     tourism
    0.07
     ink
    0.07
    _bw
    0.07
     Mobility
    0.07
    Activations Density 0.001%

    No Known Activations