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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 25101
    Prev
    Next
    INDEX
    Explanations

    core hours

    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
     type
    -0.08
     physical
    -0.08
     arithmetic
    -0.07
     Physical
    -0.07
     mass
    -0.07
     square
    -0.07
     Arithmetic
    -0.07
    .type
    -0.07
     PMID
    -0.07
     leis
    -0.06
    POSITIVE LOGITS
     Outro
    0.09
     evenings
    0.09
     redistributed
    0.08
     हुनेछ
    0.08
     Wochenende
    0.08
    focused
    0.08
    .choose
    0.08
     janela
    0.08
     भएर
    0.08
     redistribute
    0.08
    Activations Density 0.006%

    No Known Activations