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. 60936
    Prev
    Next
    INDEX
    Explanations

    MATHCOUNTS

    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
     oma
    -0.08
     cuir
    -0.08
     Roche
    -0.08
    	my
    -0.08
    (my
    -0.08
     verr
    -0.08
     torrents
    -0.07
    骨
    -0.07
    ,会
    -0.07
     curing
    -0.07
    POSITIVE LOGITS
    ్డు
    0.08
    იარ
    0.08
    �
    0.08
     Dynamic
    0.08
    არ
    0.08
     Sund
    0.07
    �
    0.07
    _INLINE
    0.07
     разработ
    0.07
    ుట
    0.07
    Activations Density 0.000%

    No Known Activations