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. 60982
    Prev
    Next
    INDEX
    Explanations

    prompt

    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
    �
    -0.10
     Fab
    -0.09
     во
    -0.09
    unp
    -0.08
     fab
    -0.08
     Stra
    -0.08
    pak
    -0.07
     incor
    -0.07
    Prot
    -0.07
    鬼
    -0.07
    POSITIVE LOGITS
     رو
    0.08
    Bg
    0.08
    函
    0.08
     absol
    0.07
     DD
    0.07
    DH
    0.07
    भाग
    0.07
     químicos
    0.07
     לח
    0.07
     AIM
    0.07
    Activations Density 0.048%

    No Known Activations