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. 15-RESID-POST-AA
    6. 18937
    Prev
    Next
    INDEX
    Explanations

    number fifteen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -0.09
    "
    -0.08
     (
    -0.08
     throughout
    -0.08
     same
    -0.08
    cut
    -0.08
    ↵↵
    -0.08
     successive
    -0.07
     TOT
    -0.07
    (or
    -0.07
    POSITIVE LOGITS
    ১৫
    0.10
    २५
    0.10
    176
    0.10
    ૧�
    0.09
    १५
    0.09
    170
    0.09
    154
    0.09
    ২৫
    0.09
    174
    0.09
    ۱۵
    0.09
    Activations Density 0.064%

    No Known Activations