© 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. 68070
    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
     jederzeit
    -0.08
    leka
    -0.08
    urig
    -0.08
     fame
    -0.08
     memas
    -0.08
     Fame
    -0.07
    _CRE
    -0.07
     wed
    -0.07
    resse
    -0.07
     Haven
    -0.07
    POSITIVE LOGITS
    (Exception
    0.08
    طات
    0.07
     commissioner
    0.07
    삼
    0.07
     Role
    0.07
    Role
    0.07
    خص
    0.07
     role
    0.07
    bass
    0.07
    role
    0.07
    Activations Density 0.003%

    No Known Activations