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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 119741
    Prev
    Next
    INDEX
    Explanations

    mathematical intervals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grammy
    -0.07
     baile
    -0.07
    ες
    -0.07
    78
    -0.07
     Blueprint
    -0.07
     incorporation
    -0.07
     Incorpor
    -0.07
    ्यास
    -0.06
    摇
    -0.06
     stan
    -0.06
    POSITIVE LOGITS
     denominator
    0.11
     denomin
    0.10
    倫理
    0.09
     консульт
    0.09
     racional
    0.09
     див
    0.09
     отриц
    0.09
     nabízí
    0.09
     parted
    0.09
     цены
    0.09
    Activations Density 0.050%

    No Known Activations