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. 30615
    Prev
    Next
    INDEX
    Explanations

    ratio

    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
     stark
    -0.09
     quello
    -0.08
    .wh
    -0.08
    اءِ
    -0.08
     wrapper
    -0.08
    chehen
    -0.07
     ತುಂಬ
    -0.07
     coherence
    -0.07
    .lock
    -0.07
    .ad
    -0.07
    POSITIVE LOGITS
    эк
    0.08
     daqueles
    0.08
     Forgotten
    0.08
     Rama
    0.07
    мов
    0.07
     Kno
    0.07
     relocated
    0.07
     Joining
    0.07
     scored
    0.07
    หัส
    0.07
    Activations Density 0.083%

    No Known Activations