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. 58748
    Prev
    Next
    INDEX
    Explanations

    equations

    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
     հայտարար
    -0.08
     socials
    -0.08
     fringe
    -0.08
     принад
    -0.08
    公众
    -0.08
     Saud
    -0.07
     seien
    -0.07
     preva
    -0.07
     əldə
    -0.07
     એર
    -0.07
    POSITIVE LOGITS
     Sonder
    0.08
     discip
    0.07
    -Par
    0.07
    _PE
    0.07
    ğraf
    0.07
    atro
    0.07
     проведение
    0.07
    _true
    0.07
    onic
    0.07
     জাম
    0.07
    Activations Density 0.000%

    No Known Activations