© 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. 19-RESID-POST-AA
    11. 102604
    Prev
    Next
    INDEX
    Explanations

    true

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ilaa
    -0.09
    /z
    -0.09
    /h
    -0.08
    ုိ
    -0.08
    ')->
    -0.08
     musste
    -0.08
     gereki
    -0.08
    /use
    -0.08
    ոլ
    -0.08
    ">'
    -0.08
    POSITIVE LOGITS
     และ
    0.18
    ，并
    0.18
    ,and
    0.16
    。そして
    0.16
     ويمكن
    0.15
    …and
    0.15
     있으며
    0.14
     ואני
    0.14
    ”和
    0.14
     futhi
    0.14
    Activations Density 0.130%

    No Known Activations