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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 56099
    Prev
    Next
    INDEX
    Explanations

    chasing and movement

    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
     ús
    -0.07
     설치
    -0.07
    -install
    -0.07
    安装
    -0.07
     instalação
    -0.07
    .variant
    -0.07
     realmente
    -0.07
    .tool
    -0.07
     repert
    -0.07
     instalado
    -0.07
    POSITIVE LOGITS
     underway
    0.10
     berger
    0.09
     ongoing
    0.09
     revenus
    0.09
     meanwhile
    0.09
     weiterhin
    0.09
    Meanwhile
    0.09
     trajectories
    0.09
     paced
    0.09
     displacement
    0.09
    Activations Density 0.020%

    No Known Activations