© 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. 7-RESID-POST-AA
    6. 1013
    Prev
    Next
    INDEX
    Explanations

    metastatic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಿಹ
    -0.09
    ത്
    -0.08
     ABS
    -0.08
     Mukama
    -0.08
     erken
    -0.08
     zugleich
    -0.08
     Mul
    -0.07
     MUL
    -0.07
     Deel
    -0.07
     Artik
    -0.07
    POSITIVE LOGITS
    нап
    0.08
    &&
    0.08
    iaz
    0.07
     tangent
    0.07
    allowed
    0.07
     изготов
    0.07
     ф
    0.07
     следует
    0.07
     строго
    0.07
     #-
    0.07
    Activations Density 0.000%

    No Known Activations