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. 11841
    Prev
    Next
    INDEX
    Explanations

    out

    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
    adı
    -0.08
     dùng
    -0.07
     altında
    -0.07
     discour
    -0.07
     dopamine
    -0.07
     kerül
    -0.07
    36
    -0.07
    MLE
    -0.07
     trae
    -0.07
     anx
    -0.07
    POSITIVE LOGITS
     thế
    0.09
    (save
    0.08
    困
    0.08
    Quit
    0.08
     söyled
    0.08
     �
    0.08
     basement
    0.08
    途中
    0.07
     свид
    0.07
     jacuzzi
    0.07
    Activations Density 0.012%

    No Known Activations