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. 49110
    Prev
    Next
    INDEX
    Explanations

    emphasis

    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
     ला
    -0.08
     बा
    -0.08
     विस्त
    -0.08
    elo
    -0.08
    istic
    -0.08
    ('\
    -0.08
     विशेष
    -0.08
     وَ
    -0.07
     ilang
    -0.07
    ("\
    -0.07
    POSITIVE LOGITS
     강조
    0.09
    强调
    0.09
     benadr
    0.09
     overdose
    0.09
     충분
    0.08
     angl
    0.08
     emphasize
    0.08
    Stephen
    0.08
    -over
    0.08
     emphasizes
    0.08
    Activations Density 0.006%

    No Known Activations