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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1396
    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_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    起来
    -0.08
    ಕ್ಕ
    -0.08
     
    -0.07
    ready
    -0.07
    anz
    -0.07
    本文
    -0.07
     zgod
    -0.07
    843
    -0.07
    ast
    -0.07
    Cent
    -0.07
    POSITIVE LOGITS
    -même
    0.12
     valleys
    0.09
     valley
    0.08
    Innen
    0.08
    /her
    0.08
    wol
    0.08
    innen
    0.08
    -mêmes
    0.08
     who've
    0.08
     hinweg
    0.08
    Activations Density 0.634%

    No Known Activations