© 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. 47489
    Prev
    Next
    INDEX
    Explanations

    Say "102"

    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
    半
    -0.09
    half
    -0.09
     half
    -0.09
     半
    -0.08
    Half
    -0.08
    _half
    -0.08
     halfway
    -0.08
    _HALF
    -0.08
    娱乐平台
    -0.07
     आईपी
    -0.07
    POSITIVE LOGITS
    16
    0.13
    256
    0.09
     passport
    0.09
    ১৬
    0.09
    96
    0.08
     وهذه
    0.08
     تطوير
    0.08
    016
    0.08
    ೈಸ
    0.08
     sixteen
    0.08
    Activations Density 0.101%

    No Known Activations