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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 26700
    Prev
    Next
    INDEX
    Explanations

    etc

    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
    oller
    -0.08
    declare
    -0.07
    -buffer
    -0.07
    awl
    -0.07
    ATIO
    -0.07
     framework
    -0.07
     prohibit
    -0.07
    Prob
    -0.07
    wah
    -0.07
    ivet
    -0.07
    POSITIVE LOGITS
     المختلفة
    0.11
     متنوعة
    0.11
     مختلفة
    0.10
     متفاوت
    0.10
     تكون
    0.09
     المختلف
    0.09
     اك
    0.09
     быць
    0.09
    funk
    0.09
     daban
    0.08
    Activations Density 0.019%

    No Known Activations