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. 76320
    Prev
    Next
    INDEX
    Explanations

    mathematical coefficients

    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
    �
    -0.09
    租
    -0.08
     clinicians
    -0.08
     novella
    -0.08
    悲
    -0.08
    Clin
    -0.08
     đau
    -0.08
     akut
    -0.08
     atra
    -0.08
     "~
    -0.08
    POSITIVE LOGITS
    Coefficient
    0.12
     coefficients
    0.11
     coefficient
    0.11
    coeff
    0.11
     coeff
    0.10
     sums
    0.10
     Fourier
    0.10
     sum
    0.10
    =sum
    0.09
     Sum
    0.09
    Activations Density 0.023%

    No Known Activations