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. 56049
    Prev
    Next
    INDEX
    Explanations

    square roots

    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
     उपकरण
    -0.08
    pex
    -0.08
    icked
    -0.08
    сып
    -0.08
     dome
    -0.07
     Wee
    -0.07
    nat
    -0.07
     hopes
    -0.07
    anez
    -0.07
    ತಿಯಿಂದ
    -0.07
    POSITIVE LOGITS
     šal
    0.08
    итайте
    0.08
    /Event
    0.08
     fanno
    0.08
     (((
    0.07
    šna
    0.07
    等等
    0.07
     oliva
    0.07
     Sandra
    0.07
    冒
    0.07
    Activations Density 0.057%

    No Known Activations