© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 5993
    Prev
    Next
    INDEX
    Explanations

    Math word problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iglio
    -0.09
    It's
    -0.08
     SMB
    -0.08
    It
    -0.08
    There's
    -0.08
     Glitter
    -0.07
     it's
    -0.07
    it's
    -0.07
    -it
    -0.07
     adorned
    -0.07
    POSITIVE LOGITS
     determine
    0.27
     શું
    0.26
     What
    0.26
     Determine
    0.26
    Determine
    0.25
     find
    0.25
     क्या
    0.25
     what
    0.24
    .What
    0.23
     Find
    0.22
    Activations Density 0.132%

    No Known Activations