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. 11900
    Prev
    Next
    INDEX
    Explanations

    Algorithms or the Pentagon

    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
    heli
    -0.08
     শত
    -0.08
     Ferd
    -0.08
     tale
    -0.08
     fringe
    -0.08
    _BTN
    -0.08
    �
    -0.08
    囲
    -0.08
     tirer
    -0.07
     journals
    -0.07
    POSITIVE LOGITS
     MTV
    0.08
     bos
    0.08
     бач
    0.07
     �
    0.07
     Clara
    0.07
    lectric
    0.07
     Danish
    0.07
     BCrypt
    0.07
    解
    0.07
     glycol
    0.07
    Activations Density 0.031%

    No Known Activations