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. 65455
    Prev
    Next
    INDEX
    Explanations

    2

    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
    اطر
    -0.08
     filas
    -0.08
    WEEN
    -0.08
     cul
    -0.08
     Nolan
    -0.07
     shoulders
    -0.07
     millions
    -0.07
     bustling
    -0.07
     fiery
    -0.07
     Rt
    -0.07
    POSITIVE LOGITS
     bij
    0.08
    0.07
     mov
    0.07
     yop
    0.07
     iff
    0.07
     remover
    0.07
     automática
    0.07
     verle
    0.07
     redistribution
    0.07
    uto
    0.07
    Activations Density 0.006%

    No Known Activations