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. 43640
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     pune
    -0.09
    chap
    -0.08
     invent
    -0.08
     schre
    -0.08
     executive
    -0.07
    γρα
    -0.07
    hebb
    -0.07
    Executive
    -0.07
    Afficher
    -0.07
    shen
    -0.07
    POSITIVE LOGITS
    。但是
    0.11
    。但
    0.10
    吗
    0.08
    。其中
    0.08
     üks
    0.08
    ,但是
    0.07
     tinggal
    0.07
    。然而
    0.07
    。当然
    0.07
    不错
    0.07
    Activations Density 0.079%

    No Known Activations