Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 12940
    Prev
    Next
    INDEX
    Explanations

    Motivation

    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
     cabel
    -0.08
     longtime
    -0.08
    ார்கள்
    -0.08
     henn
    -0.07
     taxing
    -0.07
     quell
    -0.07
    217
    -0.07
    unas
    -0.07
     transit
    -0.07
     Stable
    -0.07
    POSITIVE LOGITS
     अंत
    0.08
    方面
    0.08
     také
    0.08
     говорится
    0.08
    fulness
    0.08
     ಎಂಬ
    0.07
     draait
    0.07
    enness
    0.07
    Criterion
    0.07
     criterion
    0.07
    Activations Density 0.045%

    No Known Activations