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. 60957
    Prev
    Next
    INDEX
    Explanations

    in

    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
     соглас
    -0.08
    _du
    -0.08
     DU
    -0.08
     Gn
    -0.08
     UG
    -0.08
     التعاون
    -0.07
    DU
    -0.07
    du
    -0.07
     Сдел
    -0.07
    ুগ
    -0.07
    POSITIVE LOGITS
    stdin
    0.09
     belangstelling
    0.09
     comic
    0.09
    (circle
    0.08
     drinking
    0.08
     simpele
    0.08
     liest
    0.08
     scena
    0.08
     leyendo
    0.08
    Subscribe
    0.08
    Activations Density 0.005%

    No Known Activations