© 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. 11-RESID-POST-AA
    11. 64917
    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
     amper
    -0.09
     również
    -0.08
     따라서
    -0.08
    (am
    -0.08
    -intensive
    -0.08
     candidats
    -0.08
    ૂતો
    -0.08
     guiding
    -0.08
    ասիր
    -0.08
     পাশাপাশি
    -0.08
    POSITIVE LOGITS
     change
    0.09
     बदलाव
    0.09
     rebellious
    0.09
    lack
    0.09
    gling
    0.09
    change
    0.08
    changed
    0.08
     rebellion
    0.08
     creature
    0.08
     uprising
    0.08
    Activations Density 0.003%

    No Known Activations