© 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. 97517
    Prev
    Next
    INDEX
    Explanations

    Pers

    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
    ിസ്റ്റ
    -0.09
    иста
    -0.09
     Josh
    -0.09
    istenza
    -0.08
     Confirmation
    -0.08
    istet
    -0.08
    ист
    -0.08
     MTB
    -0.08
    ిస్ట
    -0.08
     Maver
    -0.08
    POSITIVE LOGITS
    เซีย
    0.09
    iaid
    0.09
    شل
    0.08
    sey
    0.08
    سنگ
    0.08
    880
    0.08
    ثمان
    0.08
    ULAR
    0.07
    /be
    0.07
    сӣ
    0.07
    Activations Density 0.001%

    No Known Activations