© 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. 19-RESID-POST-AA
    11. 102632
    Prev
    Next
    INDEX
    Explanations

    Words for "there"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     אומר
    -0.08
     signifie
    -0.08
     יוד
    -0.07
     agak
    -0.07
     qan
    -0.07
     קצת
    -0.07
    iang
    -0.07
     berarti
    -0.07
     FINAL
    -0.07
    auv
    -0.07
    POSITIVE LOGITS
     Allí
    0.25
     allí
    0.22
     সেখানে
    0.22
    そこ
    0.20
     అక్కడ
    0.20
     वहां
    0.20
     वहाँ
    0.20
     dort
    0.19
     وہاں
    0.19
    那里
    0.19
    Activations Density 0.041%

    No Known Activations