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. 98213
    Prev
    Next
    INDEX
    Explanations

    آ

    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
    egen
    -0.08
     chic
    -0.07
     gently
    -0.07
     perspective
    -0.07
    atég
    -0.07
     finit
    -0.07
    ىي
    -0.07
     perspectives
    -0.07
     mild
    -0.07
     decisive
    -0.07
    POSITIVE LOGITS
    تش
    0.10
    بی
    0.09
    سم
    0.09
    فت
    0.09
    ینه
    0.09
    Hin
    0.08
    ંબ
    0.08
    ویز
    0.08
    ғаш
    0.08
    ంబ
    0.08
    Activations Density 0.000%

    No Known Activations