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. 44146
    Prev
    Next
    INDEX
    Explanations

    enter

    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
    _decl
    -0.09
    jections
    -0.08
    Punch
    -0.08
     inflation
    -0.07
    Decl
    -0.07
    Infl
    -0.07
     inflam
    -0.07
    lighter
    -0.07
     Nations
    -0.07
     inflammation
    -0.07
    POSITIVE LOGITS
    odaeth
    0.09
     samun
    0.08
     למצוא
    0.08
     kupata
    0.07
     gyak
    0.07
     ès
    0.07
     պատ
    0.07
     ®
    0.07
    	mat
    0.07
     kwamba
    0.07
    Activations Density 0.012%

    No Known Activations