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. 53085
    Prev
    Next
    INDEX
    Explanations

    File paths

    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
     COPD
    -0.09
     declined
    -0.08
    alten
    -0.08
     ghj
    -0.08
    VAC
    -0.08
     Serve
    -0.07
    Fork
    -0.07
    	j
    -0.07
    ,j
    -0.07
     tweets
    -0.07
    POSITIVE LOGITS
     축
    0.08
     എത്ത
    0.07
    ীদ
    0.07
     '/',↵
    0.07
    ેમ્બર
    0.07
     trazer
    0.07
     即
    0.07
    nw
    0.07
    adeira
    0.07
    angstrom
    0.07
    Activations Density 0.002%

    No Known Activations