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. 23-RESID-POST-AA
    6. 98581
    Prev
    Next
    INDEX
    Explanations

    Emgu CV image processing

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ystate
    -0.08
     APIs
    -0.08
     strides
    -0.07
     flights
    -0.07
    Tickets
    -0.07
    ch
    -0.07
     sitt
    -0.07
     dollars
    -0.07
    hd
    -0.07
     Typed
    -0.07
    POSITIVE LOGITS
     Em
    0.11
    .Em
    0.10
    Em
    0.10
     MC
    0.10
     EM
    0.09
     ఎమ్మ
    0.09
    (em
    0.09
    	em
    0.09
     Emil
    0.09
     borde
    0.09
    Activations Density 0.001%

    No Known Activations