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. 106013
    Prev
    Next
    INDEX
    Explanations

    time

    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
    уни
    -0.09
    -0.08
     scenery
    -0.08
    یات
    -0.08
     confident
    -0.08
    ukunft
    -0.08
     musik
    -0.08
    lebn
    -0.07
     schnelle
    -0.07
    老师
    -0.07
    POSITIVE LOGITS
     exceeding
    0.10
     exceed
    0.10
     exceeds
    0.10
     ≤
    0.10
    超过
    0.09
    Estimated
    0.09
     ≥
    0.08
     <=
    0.08
     이하
    0.08
     превыш
    0.08
    Activations Density 0.019%

    No Known Activations