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. 43357
    Prev
    Next
    INDEX
    Explanations

    composition

    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
     जीवन
    -0.08
     ж
    -0.08
     삶
    -0.08
     발표
    -0.08
    	Thread
    -0.07
     life
    -0.07
    annoo
    -0.07
     inflated
    -0.07
     Онлайн
    -0.07
     semantic
    -0.07
    POSITIVE LOGITS
     daraus
    0.09
    composition
    0.09
    compose
    0.08
    -id
    0.08
     risult
    0.08
     wykon
    0.08
     choreography
    0.08
    রণের
    0.08
    behind
    0.08
     generates
    0.08
    Activations Density 0.006%

    No Known Activations