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. 54116
    Prev
    Next
    INDEX
    Explanations

    adverbs

    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
     nós
    -0.08
     precisamos
    -0.08
     soumis
    -0.08
    ávamos
    -0.07
     aktive
    -0.07
    nuts
    -0.07
    teras
    -0.07
     sensores
    -0.07
     irgendwel
    -0.07
     recentemente
    -0.07
    POSITIVE LOGITS
    痛
    0.08
     punishment
    0.07
    ങ്ക
    0.07
    	padding
    0.07
     باشد
    0.07
    	error
    0.07
    ുകൊ
    0.07
    清
    0.07
    'int
    0.07
    疼
    0.07
    Activations Density 0.000%

    No Known Activations