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. 49233
    Prev
    Next
    INDEX
    Explanations

    We

    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
     icon
    -0.08
    Normal
    -0.07
     �
    -0.07
    正常
    -0.07
     authorities
    -0.07
     sok
    -0.07
     normal
    -0.07
     Intelligent
    -0.07
     ciência
    -0.07
    -0.07
    POSITIVE LOGITS
     daunting
    0.10
    ేందుకు
    0.09
    Checklist
    0.09
     roz
    0.08
    Chuck
    0.08
     तैयार
    0.08
    .rec
    0.08
    र्�
    0.08
     предст
    0.08
     stitching
    0.08
    Activations Density 0.022%

    No Known Activations