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. 76313
    Prev
    Next
    INDEX
    Explanations

    Rewriting prompts

    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
     einge
    -0.08
    layer
    -0.08
     favorita
    -0.08
     happiest
    -0.08
    -layer
    -0.07
     eerder
    -0.07
     hela
    -0.07
     gigantes
    -0.07
    .hm
    -0.07
    talk
    -0.07
    POSITIVE LOGITS
    rest
    0.07
    asen
    0.07
    سك
    0.07
    去了
    0.07
     restantes
    0.07
     comparatively
    0.07
    Put
    0.07
     restante
    0.07
    Coming
    0.07
     تعد
    0.07
    Activations Density 0.109%

    No Known Activations