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. 15-RESID-POST-AA
    6. 19262
    Prev
    Next
    INDEX
    Explanations

    say "="

    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
    memberof
    -0.09
     मो
    -0.07
     cuore
    -0.07
     प्राथमिक
    -0.07
     cadres
    -0.07
     apre
    -0.07
     विषय
    -0.07
     Morton
    -0.07
     पो
    -0.07
     poign
    -0.07
    POSITIVE LOGITS
    Mga
    0.08
    Ending
    0.08
    .Calculate
    0.08
    álaga
    0.08
     Dá
    0.08
     gamit
    0.08
    Spacing
    0.08
    Tabela
    0.08
     között
    0.08
    kaa
    0.08
    Activations Density 0.007%

    No Known Activations