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. 15-RESID-POST-AA
    6. 142
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hum
    -0.07
    arging
    -0.07
     this
    -0.07
     fake
    -0.07
    -0.07
     aquesta
    -0.06
     MAIN
    -0.06
     AN
    -0.06
     LM
    -0.06
    -0.06
    POSITIVE LOGITS
     matimba
    0.12
     мәдәний
    0.12
     асия
    0.12
     keksoz
    0.12
     алаһ
    0.12
     дуня
    0.12
     рәһ
    0.12
     һәққ
    0.12
     пүт
    0.12
     сүп
    0.12
    Activations Density 0.069%

    No Known Activations