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. 18735
    Prev
    Next
    INDEX
    Explanations

    Smart

    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
    Ajax
    -0.09
     infiltr
    -0.09
    ajax
    -0.08
    ekile
    -0.08
     stylish
    -0.08
    inton
    -0.08
     repente
    -0.08
    hopefully
    -0.08
     sung
    -0.08
    idde
    -0.08
    POSITIVE LOGITS
     플랫폼
    0.09
     mult
    0.08
     capability
    0.08
     Platform
    0.08
     Wald
    0.08
     মাল
    0.07
     платформ
    0.07
    (mult
    0.07
     stretched
    0.07
     Mult
    0.07
    Activations Density 0.001%

    No Known Activations