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. 77352
    Prev
    Next
    INDEX
    Explanations

    Speed, time, and distance

    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
     જાહેરાત
    -0.08
     felicit
    -0.08
    ahrung
    -0.08
    ...[
    -0.08
     barking
    -0.08
     Parenting
    -0.08
     قرار
    -0.08
     Honour
    -0.07
     stimul
    -0.07
     thinker
    -0.07
    POSITIVE LOGITS
     symmetrical
    0.12
    _reverse
    0.12
     reverse
    0.12
     reversing
    0.12
     reversed
    0.11
    逆
    0.11
     తిర
    0.11
    reverse
    0.11
     mirrored
    0.11
     symmetric
    0.11
    Activations Density 0.029%

    No Known Activations