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. 111866
    Prev
    Next
    INDEX
    Explanations

    health improvements

    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
     حض
    -0.08
    \Resource
    -0.08
     techno
    -0.08
     nadr
    -0.08
     فرض
    -0.08
     Herr
    -0.08
     धर
    -0.08
    Honor
    -0.07
    stätte
    -0.07
    Award
    -0.07
    POSITIVE LOGITS
    筋
    0.09
     lace
    0.08
     температура
    0.08
     git
    0.08
     VEG
    0.08
     erit
    0.08
     кожа
    0.08
     metabolism
    0.08
     wound
    0.08
     neurological
    0.08
    Activations Density 0.009%

    No Known Activations