© 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. 99814
    Prev
    Next
    INDEX
    Explanations

    hydrogen water molecules

    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
     merchandising
    -0.09
     villain
    -0.08
    armac
    -0.08
     throne
    -0.08
    评分
    -0.08
     ornament
    -0.08
     villains
    -0.08
    िं
    -0.08
     Comic
    -0.08
     दुकान
    -0.08
    POSITIVE LOGITS
     hydrogen
    0.11
     পানি
    0.10
     voda
    0.10
     પાણી
    0.10
     OH
    0.09
     पानी
    0.09
     Hydrogen
    0.09
     water
    0.09
     الماء
    0.08
     вода
    0.08
    Activations Density 0.010%

    No Known Activations