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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 54102
    Prev
    Next
    INDEX
    Explanations

    |

    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
     exploited
    -0.09
     sandwiches
    -0.09
     পাত
    -0.09
    素材
    -0.09
    弗
    -0.08
     ditemukan
    -0.08
     utens
    -0.08
     pizza
    -0.08
    チェ
    -0.08
     বু�
    -0.08
    POSITIVE LOGITS
     objectives
    0.19
     goals
    0.18
     اهداف
    0.17
    Objectives
    0.16
     Objectives
    0.16
     목표
    0.16
    Goals
    0.16
     doelen
    0.15
     Goals
    0.15
     أهداف
    0.15
    Activations Density 0.062%

    No Known Activations