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. 48956
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     langere
    -0.08
     bearer
    -0.08
     бую
    -0.08
    �
    -0.08
     sterile
    -0.08
     capp
    -0.08
     terlebih
    -0.08
     langer
    -0.08
     чуж
    -0.07
     тили
    -0.07
    POSITIVE LOGITS
    还有
    0.07
    没有
    0.07
    ijp
    0.07
    po
    0.07
     वापस
    0.07
    ələrin
    0.07
    bd
    0.07
    ाचार
    0.07
    पाल
    0.07
     tf
    0.07
    Activations Density 0.078%

    No Known Activations