Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 43607
    Prev
    Next
    INDEX
    Explanations

    scientific/medical texts

    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
     synch
    -0.08
     kemur
    -0.08
    'ing
    -0.08
     magnet
    -0.07
    maga
    -0.07
     quen
    -0.07
    	map
    -0.07
     orsz
    -0.07
    akav
    -0.07
     laboratory
    -0.07
    POSITIVE LOGITS
     Schrift
    0.09
    스크
    0.09
     Payroll
    0.09
    scripts
    0.08
    �
    0.08
     വിമാന
    0.08
    능
    0.08
     =~
    0.07
    튼
    0.07
    ီး
    0.07
    Activations Density 0.000%

    No Known Activations