Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 130275
    Prev
    Next
    INDEX
    Explanations

    exponential functions

    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
     attentive
    -0.07
     Planet
    -0.07
    �t
    -0.07
     Wissenschaft
    -0.07
     част
    -0.07
     обязатель
    -0.07
    *r
    -0.07
     ليست
    -0.07
     rete
    -0.07
     cient
    -0.07
    POSITIVE LOGITS
    沿
    0.09
     preservatives
    0.08
    -CON
    0.08
    脂
    0.08
    marketing
    0.08
    (CON
    0.08
    Pics
    0.08
    营销
    0.08
     Madeleine
    0.08
    .Zone
    0.08
    Activations Density 0.008%

    No Known Activations