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. 58550
    Prev
    Next
    INDEX
    Explanations

    math problems/operations

    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
    PLI
    -0.08
     totaling
    -0.07
    েখানে
    -0.07
    -space
    -0.07
    PR
    -0.07
    ੱਚ
    -0.07
    anity
    -0.07
    års
    -0.07
    ,以及
    -0.07
     clicking
    -0.07
    POSITIVE LOGITS
     voorbere
    0.09
     Prepar
    0.09
    Prepar
    0.08
     hud
    0.08
     Variable
    0.08
     Justicia
    0.08
    Prepared
    0.08
     Prepared
    0.08
     Input
    0.07
     fem
    0.07
    Activations Density 0.002%

    No Known Activations