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. 30595
    Prev
    Next
    INDEX
    Explanations

    conclusion

    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
     majority
    -0.07
    530
    -0.07
     along
    -0.07
     smack
    -0.07
     factoring
    -0.07
     emancip
    -0.07
    -0.07
     cutting
    -0.07
     Maximum
    -0.06
    .ev
    -0.06
    POSITIVE LOGITS
     намер
    0.09
     نقط
    0.09
     поговор
    0.09
    _outline
    0.08
     खु
    0.08
    apit
    0.08
     заключ
    0.08
     chapitre
    0.08
    וז
    0.08
     ముగ
    0.08
    Activations Density 0.005%

    No Known Activations