© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 629
    Prev
    Next
    INDEX
    Explanations

    Marketing and sharing incentives

    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
     вн
    -0.09
    beiter
    -0.07
     педагог
    -0.07
    l
    -0.07
     воспит
    -0.07
     развит
    -0.07
     enfat
    -0.07
    <Type
    -0.07
    Development
    -0.07
    First
    -0.07
    POSITIVE LOGITS
     fined
    0.09
     cheap
    0.09
    unlock
    0.08
     pleaded
    0.08
     Unlock
    0.08
     filing
    0.08
    ，据
    0.08
    laag
    0.08
     günstig
    0.08
     cheaper
    0.08
    Activations Density 0.019%

    No Known Activations