© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6465
    Prev
    Next
    INDEX
    Explanations

    Application

    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
    дерінің
    -0.08
     servlet
    -0.08
    /images
    -0.07
     distr
    -0.07
    /image
    -0.07
     visual
    -0.07
    .servlet
    -0.07
    /screens
    -0.07
     görünt
    -0.07
     screens
    -0.07
    POSITIVE LOGITS
    Record
    0.12
    .Record
    0.11
     Record
    0.11
    _record
    0.11
     record
    0.10
    _RECORD
    0.09
    .record
    0.09
    126
    0.09
     기록
    0.09
    _Record
    0.09
    Activations Density 0.001%

    No Known Activations