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. 15-RESID-POST-AA
    6. 19287
    Prev
    Next
    INDEX
    Explanations

    Foreign conjunctions

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.08
    "
    -0.08
    we
    -0.08
    `
    -0.07
    (t
    -0.07
    :
    -0.07
    に
    -0.07
    (num
    -0.07
    双方
    -0.07
    .↵↵
    -0.07
    POSITIVE LOGITS
     valamint
    0.16
     illetve
    0.16
     сондай
    0.14
     odnosno
    0.13
     voire
    0.13
     როგორიც
    0.13
     কিংবা
    0.13
     например
    0.12
     включая
    0.12
     ataupun
    0.12
    Activations Density 0.372%

    No Known Activations