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. 55914
    Prev
    Next
    INDEX
    Explanations

    Image generation 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
    (ed
    -0.08
    (DIS
    -0.08
    Allow
    -0.08
     sonora
    -0.08
    alur
    -0.07
     처리
    -0.07
    FY
    -0.07
     frecuentes
    -0.07
     Cyr
    -0.07
    wartz
    -0.07
    POSITIVE LOGITS
     vivid
    0.09
     нос
    0.08
    599
    0.08
     obrá
    0.08
     intrinsic
    0.08
     quasi
    0.07
     vascular
    0.07
     portable
    0.07
     عرض
    0.07
     exempl
    0.07
    Activations Density 0.009%

    No Known Activations