© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 114182
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
    leyen
    -0.08
     plot
    -0.08
     pose
    -0.08
     plasm
    -0.07
    layout
    -0.07
     plots
    -0.07
    Scripts
    -0.07
     technisch
    -0.07
    nab
    -0.07
    ecur
    -0.07
    POSITIVE LOGITS
    ället
    0.09
     어
    0.08
    }))
    0.08
    στηκε
    0.08
     అంట
    0.08
    ియా
    0.08
     �
    0.08
    :url
    0.08
    patched
    0.08
     exfol
    0.08
    Activations Density 0.006%

    No Known Activations