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. 15-RESID-POST-AA
    6. 19504
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afy
    -0.11
     superbe
    -0.08
    lander
    -0.08
    square
    -0.08
    σει
    -0.08
     ಮೇಲೆ
    -0.08
     عليه
    -0.08
    वर
    -0.08
    Hopefully
    -0.08
    orrer
    -0.08
    POSITIVE LOGITS
     malen
    0.08
    .ssl
    0.08
     Dirección
    0.08
     Redis
    0.07
     endure
    0.07
     panjang
    0.07
     SMTP
    0.07
     SSL
    0.07
     retained
    0.07
     drugih
    0.07
    Activations Density 0.000%

    No Known Activations