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. 113060
    Prev
    Next
    INDEX
    Explanations

    dusting dough

    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
     públic
    -0.08
     batterij
    -0.08
     Kryptow
    -0.08
     Battery
    -0.08
    spiracy
    -0.08
    vum
    -0.07
     Durchschnitt
    -0.07
    cox
    -0.07
     Testimonials
    -0.07
     öffentlich
    -0.07
    POSITIVE LOGITS
     slips
    0.08
     preparación
    0.08
     nhớ
    0.07
     angka
    0.07
     zd
    0.07
     lubric
    0.07
     industria
    0.07
    UInt
    0.07
     rye
    0.07
     hjemme
    0.07
    Activations Density 0.011%

    No Known Activations