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. 60651
    Prev
    Next
    INDEX
    Explanations

    suffer

    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
     Thur
    -0.08
     Tad
    -0.08
     larg
    -0.08
     Hanson
    -0.08
     Forder
    -0.08
     Wanted
    -0.07
    oyant
    -0.07
     Hinter
    -0.07
    _PATCH
    -0.07
    渠
    -0.07
    POSITIVE LOGITS
     suffering
    0.10
     suffered
    0.09
    痛
    0.09
    困
    0.08
     orde
    0.08
     về
    0.08
     endured
    0.08
     cat
    0.08
    苦
    0.07
     suffer
    0.07
    Activations Density 0.012%

    No Known Activations