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. 58618
    Prev
    Next
    INDEX
    Explanations

    Underlying concepts

    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
    инин
    -0.07
    833
    -0.07
     steril
    -0.07
    161
    -0.07
     Falcon
    -0.07
    롭게
    -0.07
     Auditor
    -0.07
     الحصول
    -0.07
     在
    -0.07
    าที
    -0.07
    POSITIVE LOGITS
     وراء
    0.15
     underlying
    0.15
     behind
    0.14
    liggende
    0.14
     beneath
    0.14
     derrière
    0.13
     detrás
    0.13
     Behind
    0.13
     underpin
    0.13
    Behind
    0.12
    Activations Density 0.046%

    No Known Activations