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. 389
    Prev
    Next
    INDEX
    Explanations

    /im

    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
     inds
    -0.08
     muck
    -0.08
    omelo
    -0.08
    -"+
    -0.07
     foo
    -0.07
    editable
    -0.07
     gona
    -0.07
     discussie
    -0.07
    Indices
    -0.07
    onces
    -0.07
    POSITIVE LOGITS
    0.08
     учиты
    0.08
    	s
    0.07
    oda
    0.07
     devotees
    0.07
     сиг
    0.07
     matières
    0.07
     ист
    0.07
     از
    0.07
    zd
    0.07
    Activations Density 0.002%

    No Known Activations