© 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. 3-RESID-POST-AA
    11. 2578
    Prev
    Next
    INDEX
    Explanations

    ない

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     serp
    -0.07
     caution
    -0.07
     breakpoint
    -0.07
     churr
    -0.07
     wherein
    -0.07
     Colonel
    -0.07
     Cartoon
    -0.07
     दिव
    -0.07
     cartoon
    -0.07
    cak
    -0.07
    POSITIVE LOGITS
     �
    0.09
     lá
    0.08
    �
    0.08
     Lan
    0.08
    �
    0.08
     Sidd
    0.08
    令人
    0.07
    τί
    0.07
    meg
    0.07
    締
    0.07
    Activations Density 0.001%

    No Known Activations