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. 23-RESID-POST-AA
    6. 98014
    Prev
    Next
    INDEX
    Explanations

    the ending -ers, -lar, -undy

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    遣
    -0.09
    كس
    -0.09
     кист
    -0.08
    ท์
    -0.08
    ريف
    -0.08
    径
    -0.08
     orthodox
    -0.08
    цина
    -0.08
     kuts
    -0.08
    เลข
    -0.07
    POSITIVE LOGITS
    emeester
    0.14
    undy
    0.13
    ers
    0.11
    erschap
    0.11
    andy
    0.10
    lar
    0.10
    ess
    0.10
    uesia
    0.09
    oy
    0.09
    esses
    0.09
    Activations Density 0.007%

    No Known Activations