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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 56158
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    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
    okee
    -0.08
     નહ
    -0.08
     રાખ
    -0.08
     abe
    -0.08
    嫩
    -0.07
     nue
    -0.07
     rms
    -0.07
     unfavorable
    -0.07
    _sb
    -0.07
     emailed
    -0.07
    POSITIVE LOGITS
     topics
    0.12
     discusses
    0.11
     وكيف
    0.11
    如何
    0.10
     chapter
    0.10
     seminar
    0.10
    topics
    0.10
    Topics
    0.09
     चर्चा
    0.09
     আলোচনা
    0.09
    Activations Density 0.092%

    No Known Activations