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. 78603
    Prev
    Next
    INDEX
    Explanations

    computer science, technology

    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
    ER
    -0.08
    ذن
    -0.07
    .training
    -0.07
     strictly
    -0.07
     laut
    -0.07
    Training
    -0.07
     मर
    -0.07
     would've
    -0.07
     ताल
    -0.07
    .mine
    -0.07
    POSITIVE LOGITS
    」は
    0.10
    _cs
    0.10
     என்பது
    0.10
    (cs
    0.09
     adalah
    0.09
     merupakan
    0.09
     представляет
    0.08
     #-}↵↵
    0.08
    是一
    0.08
     :=↵
    0.08
    Activations Density 0.151%

    No Known Activations