Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 49586
    Prev
    Next
    INDEX
    Explanations

    need

    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
     profits
    -0.08
     horrifying
    -0.08
     uburyo
    -0.07
     lan
    -0.07
    өгөн
    -0.07
     chast
    -0.07
     electives
    -0.07
     pressing
    -0.07
    körper
    -0.07
     rap
    -0.07
    POSITIVE LOGITS
     لتحقيق
    0.10
     لت
    0.09
     لتن
    0.08
     تحقيق
    0.08
     لتح
    0.08
     لاست
    0.08
     Moy
    0.08
     اللازمة
    0.08
    Successfully
    0.08
     infra
    0.08
    Activations Density 0.052%

    No Known Activations