Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 112304
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    jon
    -0.07
     downhill
    -0.07
     trabalhando
    -0.07
     åt
    -0.07
    esson
    -0.07
     Ca
    -0.07
     Young
    -0.07
     ruled
    -0.07
    ainfo
    -0.07
    andingan
    -0.07
    POSITIVE LOGITS
     gesammelt
    0.11
     unanswered
    0.10
     FAQs
    0.10
     gesteld
    0.09
     bese
    0.09
     Stitch
    0.08
    FAQs
    0.08
     traiter
    0.08
     prioritized
    0.08
    .answers
    0.08
    Activations Density 0.037%

    No Known Activations