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. 30600
    Prev
    Next
    INDEX
    Explanations

    is

    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
     zato
    -0.08
     tais
    -0.07
    .yahoo
    -0.07
    از
    -0.07
    ె
    -0.07
    э
    -0.07
     dichos
    -0.07
    افی
    -0.07
    Yi
    -0.07
     पड़
    -0.07
    POSITIVE LOGITS
     whirl
    0.09
     nein
    0.08
     mites
    0.08
    0.07
    ucune
    0.07
     ninguno
    0.07
    ょ
    0.07
     arab
    0.07
     kindly
    0.07
     घ
    0.07
    Activations Density 0.062%

    No Known Activations