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. 48779
    Prev
    Next
    INDEX
    Explanations

    Stretching instructions

    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
    Interfaces
    -0.08
    提交
    -0.08
    ς
    -0.08
    Consumes
    -0.07
     communications
    -0.07
    彩票
    -0.07
    _interfaces
    -0.07
    Commun
    -0.07
    Interface
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     расслаб
    0.10
     gently
    0.09
    pendicular
    0.09
     relaxing
    0.09
     কোম
    0.09
     relaxation
    0.09
     Relax
    0.09
     relaj
    0.09
     easiest
    0.08
     gentle
    0.08
    Activations Density 0.009%

    No Known Activations