Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43163
    Prev
    Next
    INDEX
    Explanations

    is

    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
     screening
    -0.09
    -Mail
    -0.08
     delicate
    -0.08
     thresholds
    -0.08
     Screening
    -0.08
    .delete
    -0.07
     Aleks
    -0.07
    압
    -0.07
    -LAST
    -0.07
    -reset
    -0.07
    POSITIVE LOGITS
    相信
    0.10
     বিশ্বাস
    0.09
    ,相
    0.09
     believe
    0.09
    belief
    0.08
     믿
    0.08
     concret
    0.08
    Believe
    0.08
     विश्वास
    0.08
     croy
    0.08
    Activations Density 0.016%

    No Known Activations