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. 53831
    Prev
    Next
    INDEX
    Explanations

    Specificity and immediacy

    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
     Ivan
    -0.08
     públicos
    -0.07
     Balm
    -0.07
     Alberto
    -0.07
     General
    -0.07
     generales
    -0.07
     திற
    -0.07
     Públic
    -0.07
     Ine
    -0.07
     இன
    -0.07
    POSITIVE LOGITS
    甚至
    0.09
     voire
    0.09
    且
    0.08
    、更
    0.08
    ’y
    0.08
     marchand
    0.08
    Sher
    0.08
    ਸੀ
    0.08
    yh
    0.08
    、不
    0.08
    Activations Density 0.222%

    No Known Activations