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. 52846
    Prev
    Next
    INDEX
    Explanations

    numerical methods

    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
     refunded
    -0.09
     Rebecca
    -0.09
    irenze
    -0.09
     autores
    -0.08
    department
    -0.08
    Tickets
    -0.08
    ्रोत
    -0.08
     overseeing
    -0.08
     влож
    -0.08
     จังหวัด
    -0.08
    POSITIVE LOGITS
     approximation
    0.13
     approxim
    0.12
     discret
    0.12
    近
    0.11
     approximate
    0.10
     practical
    0.10
     aproxim
    0.09
     chop
    0.09
     aproxima
    0.09
    approx
    0.09
    Activations Density 0.008%

    No Known Activations