© 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. 7-RESID-POST-AA
    11. 1445
    Prev
    Next
    INDEX
    Explanations

    .g

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sorry
    -0.08
    мини
    -0.08
     siap
    -0.07
     Sorry
    -0.07
     sufficiently
    -0.07
     senc
    -0.07
     Lucky
    -0.07
     hurt
    -0.07
     irgendwie
    -0.07
     lena
    -0.07
    POSITIVE LOGITS
    ുണ്ട
    0.08
    camp
    0.08
     ਨ
    0.08
    น
    0.08
    Corp
    0.07
    anska
    0.07
     discipline
    0.07
     assessments
    0.07
    ansk
    0.07
    folk
    0.07
    Activations Density 0.022%

    No Known Activations