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. 113054
    Prev
    Next
    INDEX
    Explanations

    sales

    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
    )throws
    -0.08
     Organização
    -0.08
    }/${
    -0.08
     interessant
    -0.08
     fosse
    -0.07
     Organisation
    -0.07
    公网
    -0.07
     corrig
    -0.07
     BUF
    -0.07
     Correction
    -0.07
    POSITIVE LOGITS
     sales
    0.10
     referrals
    0.09
     bisnis
    0.09
     बिक्री
    0.09
    sales
    0.09
     directa
    0.09
     actionable
    0.09
     ventas
    0.09
     Umsatz
    0.09
     keputusan
    0.08
    Activations Density 0.040%

    No Known Activations