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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45324
    Prev
    Next
    INDEX
    Explanations

    external microphones

    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
     replaced
    -0.09
    ▫
    -0.08
     replaces
    -0.08
     football
    -0.08
     quotas
    -0.08
    IDL
    -0.08
    足球
    -0.07
    �
    -0.07
     ersetzen
    -0.07
     bounds
    -0.07
    POSITIVE LOGITS
     बेहतर
    0.08
     recue
    0.08
     удел
    0.08
     хороший
    0.08
     المحمول
    0.08
     amélior
    0.08
     الهواء
    0.08
     recorder
    0.08
     മികച്ച
    0.08
     улучш
    0.08
    Activations Density 0.003%

    No Known Activations