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. 18971
    Prev
    Next
    INDEX
    Explanations

    Company designation

    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
     voilà
    -0.09
     кезде
    -0.09
     espl
    -0.09
     voila
    -0.09
    νει
    -0.08
    ువాత
    -0.08
     esf
    -0.08
     cuir
    -0.08
     traje
    -0.08
    ξε
    -0.08
    POSITIVE LOGITS
     Ltd
    0.16
    有限公司
    0.14
    旗下
    0.13
     Gmb
    0.13
     LLC
    0.12
     Corporation
    0.12
     Pvt
    0.12
    株式会社
    0.11
     Pty
    0.10
     Corp
    0.10
    Activations Density 0.113%

    No Known Activations