© 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. 29760
    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
     gesprek
    -0.08
     Umgebung
    -0.08
     vicinity
    -0.08
    ibraries
    -0.07
    �牌
    -0.07
     لاعب
    -0.07
     Pace
    -0.07
     omgeving
    -0.07
     Umfeld
    -0.07
     قال
    -0.07
    POSITIVE LOGITS
    _Device
    0.08
    .randn
    0.08
     unnoticed
    0.08
     Hostel
    0.08
    edin
    0.07
    �
    0.07
     анал
    0.07
    Ls
    0.07
    amela
    0.07
     thai
    0.07
    Activations Density 0.003%

    No Known Activations