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. 102675
    Prev
    Next
    INDEX
    Explanations

    Arithmetic computations

    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
    .Id
    -0.09
    નાં
    -0.08
    .View
    -0.08
    传奇
    -0.08
    之后
    -0.08
    .Meta
    -0.07
     માટે
    -0.07
     સુધી
    -0.07
     legendary
    -0.07
    .Decode
    -0.07
    POSITIVE LOGITS
    الن
    0.08
    Wechat
    0.08
     écoute
    0.08
     etwa
    0.08
    093
    0.08
     Potter
    0.08
     rods
    0.08
    Cet
    0.08
     উৎস
    0.08
     Caj
    0.07
    Activations Density 0.199%

    No Known Activations