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

    Neuronpedia

    APICircuit 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. 12966
    Prev
    Next
    INDEX
    Explanations

    News and intelligence reports

    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
     sujeitos
    -0.08
     yace
    -0.08
    898
    -0.08
     anual
    -0.07
     controla
    -0.07
     mastering
    -0.07
     implica
    -0.07
     temas
    -0.07
    =Request
    -0.07
    	operator
    -0.07
    POSITIVE LOGITS
     errone
    0.12
     inaccurate
    0.12
     erroneous
    0.11
     inaccur
    0.11
     falsely
    0.11
     अनुमान
    0.11
     mistaken
    0.11
     prematurely
    0.10
     incorrectly
    0.10
     incorrect
    0.10
    Activations Density 0.045%

    No Known Activations