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. 78524
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
     ubr
    -0.08
    шем
    -0.07
     douce
    -0.07
    pat
    -0.07
    ową
    -0.07
    slow
    -0.07
    āl
    -0.07
    lde
    -0.07
    šo
    -0.07
    ést
    -0.07
    POSITIVE LOGITS
     THE
    0.09
     SYSTEM
    0.09
     GENERAL
    0.09
     HERE
    0.09
     PUBLIC
    0.08
     siin
    0.08
     PRESIDENT
    0.08
     NON
    0.08
     направления
    0.08
     GAME
    0.08
    Activations Density 0.128%

    No Known Activations