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. 117489
    Prev
    Next
    INDEX
    Explanations

    stem

    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
     див
    -0.08
     reten
    -0.08
     elsif
    -0.08
     вызыва
    -0.07
    elsif
    -0.07
     тем
    -0.07
    тесь
    -0.07
    taf
    -0.07
     feb
    -0.07
    calloc
    -0.07
    POSITIVE LOGITS
    شار
    0.09
     filed
    0.09
     નં
    0.08
     destruction
    0.08
     Interstate
    0.08
     asparagus
    0.07
     bleibt
    0.07
     Mango
    0.07
    poons
    0.07
    剪
    0.07
    Activations Density 0.002%

    No Known Activations