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. 7-RESID-POST-AA
    6. 130975
    Prev
    Next
    INDEX
    Explanations

    script

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ler
    -0.09
     Mother
    -0.08
     daily
    -0.08
     Pard
    -0.08
    -0.08
    Lm
    -0.07
     DAILY
    -0.07
     Daily
    -0.07
    ITER
    -0.07
     liz
    -0.07
    POSITIVE LOGITS
     geführt
    0.08
    babel
    0.08
    ucene
    0.07
    때
    0.07
     ಮಾರ
    0.07
    אנ
    0.07
    ogen
    0.07
    柜
    0.07
    省
    0.07
    lub
    0.07
    Activations Density 0.002%

    No Known Activations