© 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. 70797
    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
     Rosen
    -0.07
     evolving
    -0.07
    annie
    -0.07
    کم
    -0.07
     roku
    -0.07
     embellished
    -0.07
     culminating
    -0.07
     ém
    -0.07
    ibaba
    -0.07
     reminiscent
    -0.07
    POSITIVE LOGITS
     possessions
    0.10
    /her
    0.09
     guys
    0.09
     own
    0.09
    自己的
    0.09
    Own
    0.09
     alleine
    0.08
     else's
    0.08
    -même
    0.08
     verksam
    0.08
    Activations Density 0.039%

    No Known Activations