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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 30674
    Prev
    Next
    INDEX
    Explanations

    improvements, systems, satisfaction

    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
     concerning
    -0.08
    (Is
    -0.08
     customizable
    -0.07
    imbus
    -0.07
     �
    -0.07
    ifference
    -0.06
     обесп
    -0.06
     configurable
    -0.06
    окол
    -0.06
    υμα
    -0.06
    POSITIVE LOGITS
     باعث
    0.10
     इससे
    0.10
     aitab
    0.10
     desto
    0.10
     voorkomt
    0.10
     infatti
    0.10
     sayesinde
    0.10
    르면
    0.10
     করলে
    0.09
     totiž
    0.09
    Activations Density 0.140%

    No Known Activations