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. 129939
    Prev
    Next
    INDEX
    Explanations

    of

    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
     overw
    -0.08
     venues
    -0.08
     cauc
    -0.08
    -login
    -0.08
     horseback
    -0.08
     venue
    -0.07
     Cauc
    -0.07
    -aga
    -0.07
    -worthy
    -0.07
     Ukrainian
    -0.07
    POSITIVE LOGITS
    quantity
    0.11
     количе
    0.10
     quantidade
    0.09
     quantities
    0.09
    cantidad
    0.09
     प्रति
    0.09
     lượng
    0.09
     كمية
    0.09
    สัมพันธ์
    0.09
     combien
    0.09
    Activations Density 0.004%

    No Known Activations