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. 446
    Prev
    Next
    INDEX
    Explanations

    Coming to life

    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
     stos
    -0.08
    用于
    -0.08
     Episode
    -0.07
    截
    -0.07
     ou
    -0.07
    verständlich
    -0.07
    mgr
    -0.07
    эп
    -0.07
     treino
    -0.07
    itul
    -0.07
    POSITIVE LOGITS
     움직
    0.12
    Animated
    0.12
     animated
    0.12
     anim
    0.12
     levende
    0.12
     animé
    0.11
    animated
    0.11
    Animating
    0.11
    Animator
    0.11
     ож
    0.11
    Activations Density 0.108%

    No Known Activations