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. 76071
    Prev
    Next
    INDEX
    Explanations

    called

    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
     softened
    -0.08
    :B
    -0.08
     fournisseurs
    -0.08
    .up
    -0.08
     blacks
    -0.08
     whitening
    -0.08
     transluc
    -0.07
     sonder
    -0.07
    -up
    -0.07
    ifra
    -0.07
    POSITIVE LOGITS
     ور
    0.09
     imaginary
    0.08
    Imagine
    0.08
     خط
    0.08
     ય
    0.08
     Mavericks
    0.08
     Yol
    0.08
    เพลง
    0.08
     Imagine
    0.07
     hypothetical
    0.07
    Activations Density 0.076%

    No Known Activations