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. 119875
    Prev
    Next
    INDEX
    Explanations

    exhaust

    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
    Sec
    -0.08
     øst
    -0.08
    Ment
    -0.08
    幅
    -0.07
     осуществ
    -0.07
     ment
    -0.07
     autograph
    -0.07
    DY
    -0.07
    наз
    -0.07
     ped
    -0.07
    POSITIVE LOGITS
    掉
    0.08
     possibilities
    0.08
    �
    0.07
     Eg
    0.07
     Violet
    0.07
     exhausting
    0.07
     Mich
    0.07
     Exhaust
    0.07
     validating
    0.07
     steam
    0.07
    Activations Density 0.005%

    No Known Activations