© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54901
    Prev
    Next
    INDEX
    Explanations

    speech

    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
    ുള്ള
    -0.08
     reads
    -0.08
     validate
    -0.08
     municipality
    -0.07
     multiplication
    -0.07
    -0.07
     multiply
    -0.07
     बनी
    -0.07
     allow
    -0.07
    -0.07
    POSITIVE LOGITS
     keynote
    0.10
     বক্ত
    0.10
     speeches
    0.10
     발표
    0.09
     참석
    0.09
    壇
    0.09
     제목
    0.09
     Stanford
    0.09
     презента
    0.09
    চার
    0.09
    Activations Density 0.050%

    No Known Activations