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. 12342
    Prev
    Next
    INDEX
    Explanations

    CF

    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
    пал
    -0.08
     Reich
    -0.08
    _notice
    -0.08
    reem
    -0.07
    _attribute
    -0.07
     amput
    -0.07
     ohnehin
    -0.07
    �
    -0.07
    פס
    -0.07
     plaintiffs
    -0.07
    POSITIVE LOGITS
     calcul
    0.09
    ্ধ
    0.07
    ্ণ
    0.07
    是多少
    0.07
     নেই
    0.07
    (Binary
    0.07
     בין
    0.07
    (Group
    0.07
     calculator
    0.07
    ulong
    0.07
    Activations Density 0.012%

    No Known Activations