Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130889
    Prev
    Next
    INDEX
    Explanations

    quant

    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
     gigantes
    -0.09
     rental
    -0.09
    Rental
    -0.08
     jil
    -0.08
     Jeans
    -0.08
     juvenile
    -0.08
     adul
    -0.08
     paralelo
    -0.08
     acres
    -0.08
    .Surface
    -0.08
    POSITIVE LOGITS
     quant
    0.18
    .quant
    0.15
     requ
    0.15
     Quant
    0.14
    Quant
    0.14
     INT
    0.14
     quan
    0.14
    _quant
    0.13
    quant
    0.13
    量
    0.13
    Activations Density 0.005%

    No Known Activations