© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7613
    Prev
    Next
    INDEX
    Explanations

    adhesion

    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
     су
    -0.08
    aked
    -0.08
    assade
    -0.08
     Katr
    -0.08
     republ
    -0.07
    ellipse
    -0.07
     hals
    -0.07
     dictator
    -0.07
     Raymond
    -0.07
     höf
    -0.07
    POSITIVE LOGITS
     adhesion
    0.11
     anch
    0.09
     bonding
    0.09
     discontinu
    0.09
     cohesion
    0.08
     bridging
    0.08
     asphalt
    0.08
    Attachment
    0.08
    =true
    0.08
    attachment
    0.08
    Activations Density 0.014%

    No Known Activations