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. 42230
    Prev
    Next
    INDEX
    Explanations

    of

    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
     obstacles
    -0.09
     الإجراءات
    -0.08
    Obstacle
    -0.08
     overcome
    -0.08
     everything
    -0.08
     apert
    -0.08
     embarking
    -0.07
     Obst
    -0.07
     launch
    -0.07
    EVER
    -0.07
    POSITIVE LOGITS
    �
    0.09
     vina
    0.08
     dals
    0.08
     Ryan
    0.08
     éventuellement
    0.08
     invloed
    0.08
    ဒီ
    0.08
    рим
    0.07
     Worc
    0.07
     hvilken
    0.07
    Activations Density 0.007%

    No Known Activations