© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16533
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -0.13
    	this
    -0.12
     these
    -0.12
     tüm
    -0.10
     هذه
    -0.10
     эту
    -0.10
     questa
    -0.10
     tätä
    -0.10
    .SUCCESS
    -0.10
     acest
    -0.10
    POSITIVE LOGITS
    ,
    0.10
    、
    0.09
     That
    0.09
    ،
    0.09
    ',
    0.08
     कि
    0.08
    、その
    0.08
     example
    0.08
     =
    0.07
     -
    0.07
    Activations Density 0.024%

    No Known Activations