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. 120285
    Prev
    Next
    INDEX
    Explanations

    math

    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
     ваг
    -0.08
     masterpieces
    -0.08
     parametro
    -0.07
    CAR
    -0.07
     emitir
    -0.07
     Dal
    -0.07
     COMPONENT
    -0.07
    Dal
    -0.07
     they've
    -0.07
    ###
    -0.07
    POSITIVE LOGITS
     foodie
    0.08
     candy
    0.08
     Rong
    0.08
     bartender
    0.08
     Lava
    0.08
    ultz
    0.07
     qualité
    0.07
     folie
    0.07
    лем
    0.07
     diversão
    0.07
    Activations Density 0.000%

    No Known Activations