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. 76471
    Prev
    Next
    INDEX
    Explanations

    book excerpts

    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
     LGBTQ
    -0.11
     indie
    -0.10
     �
    -0.10
     �
    -0.10
     LGBT
    -0.09
     �
    -0.09
     esports
    -0.09
     certifications
    -0.09
     onboarding
    -0.09
     millennials
    -0.09
    POSITIVE LOGITS
     daß
    0.11
    ,—
    0.11
     diminution
    0.10
     proprietor
    0.10
     scarcely
    0.10
    Vien
    0.10
     nobles
    0.10
     remarked
    0.10
     thereto
    0.09
     Vienna
    0.09
    Activations Density 0.464%

    No Known Activations