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. 76477
    Prev
    Next
    INDEX
    Explanations

    A/B testing and iteration

    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
    CAS
    -0.08
    Hm
    -0.08
    hm
    -0.08
    Privileges
    -0.07
     جمعية
    -0.07
    法院
    -0.07
     справ
    -0.07
    中华人民共和国
    -0.07
    Rpc
    -0.07
    COMM
    -0.07
    POSITIVE LOGITS
     tweaking
    0.12
     experimenting
    0.11
     optimizing
    0.11
    优化
    0.11
    改善
    0.10
     experimented
    0.10
     amélior
    0.10
     Tested
    0.10
     Optimize
    0.10
     tweak
    0.10
    Activations Density 0.016%

    No Known Activations