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

    Neuronpedia

    APICircuit 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. 43918
    Prev
    Next
    INDEX
    Explanations

    arithmetic word problems

    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
     lima
    -0.08
     promising
    -0.08
     Lima
    -0.08
     testify
    -0.08
     fruition
    -0.08
    луб
    -0.08
     flooded
    -0.07
    limits
    -0.07
    LTR
    -0.07
     androgen
    -0.07
    POSITIVE LOGITS
     gleicher
    0.09
     alike
    0.09
     ஆகிய
    0.09
     coexist
    0.08
    之间
    0.08
     đều
    0.08
    俱
    0.08
     બંને
    0.08
    }px
    0.08
     begge
    0.07
    Activations Density 0.044%

    No Known Activations