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. 54075
    Prev
    Next
    INDEX
    Explanations

    一

    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
     whiten
    -0.08
     HGH
    -0.08
    >;↵↵
    -0.08
     Ember
    -0.08
    	mat
    -0.08
     �
    -0.08
     Whitening
    -0.07
    >;↵
    -0.07
     Greenwood
    -0.07
     VOA
    -0.07
    POSITIVE LOGITS
    je
    0.09
    -sama
    0.08
     butt
    0.08
     Studie
    0.07
     брат
    0.07
    ero
    0.07
    �
    0.07
     televiz
    0.07
    休
    0.07
    Study
    0.07
    Activations Density 0.002%

    No Known Activations