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. 23-RESID-POST-AA
    6. 98076
    Prev
    Next
    INDEX
    Explanations

    Works

    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
     posao
    -0.10
    _FORCE
    -0.09
     boulot
    -0.09
     rumo
    -0.08
     carrer
    -0.08
     overflow
    -0.08
     werkdagen
    -0.08
     обратно
    -0.08
    ขัน
    -0.08
     бизнеса
    -0.08
    POSITIVE LOGITS
     cited
    0.18
     consulted
    0.14
     citado
    0.14
     reviewed
    0.11
     referenced
    0.11
     Reviewed
    0.11
     المذك
    0.11
     mentioned
    0.11
     citar
    0.11
     Consult
    0.11
    Activations Density 0.016%

    No Known Activations