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. 12520
    Prev
    Next
    INDEX
    Explanations

    Equations

    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
     varten
    -0.08
    지원
    -0.08
    ілді
    -0.07
     nacido
    -0.07
    ächst
    -0.07
    .pkl
    -0.07
     신고
    -0.07
    암
    -0.07
    Confirm
    -0.07
     ingres
    -0.07
    POSITIVE LOGITS
     gradients
    0.09
    涙
    0.08
     mai
    0.08
     大连
    0.08
     �
    0.08
     Mead
    0.08
     �
    0.08
     wix
    0.08
     名人
    0.08
     学
    0.08
    Activations Density 0.002%

    No Known Activations