© 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. 102258
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ifizieren
    -0.09
     meningkatkan
    -0.08
     ntxiv
    -0.08
     раду
    -0.08
     बढ़
    -0.07
     Reykj
    -0.07
     zwięks
    -0.07
    .")↵↵
    -0.07
    ifik
    -0.07
    _system
    -0.07
    POSITIVE LOGITS
     litt
    0.09
     Charset
    0.08
    ednes
    0.08
    沒
    0.08
    Publicidade
    0.08
    edata
    0.08
    如此
    0.08
    ’↵
    0.08
     tenancy
    0.08
    】【
    0.07
    Activations Density 0.000%

    No Known Activations