© 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. 102895
    Prev
    Next
    INDEX
    Explanations

    Translations of "inside"

    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
     ogé
    -0.08
     어디
    -0.08
     etiam
    -0.08
     tudi
    -0.07
     CITY
    -0.07
    endphp
    -0.07
     roue
    -0.07
     battlefield
    -0.07
     coast
    -0.07
     настав
    -0.07
    POSITIVE LOGITS
    进去
    0.22
     dedans
    0.20
     সেখানে
    0.19
     dessus
    0.19
     उसमें
    0.17
    在那里
    0.16
     وہاں
    0.16
     वहां
    0.16
     hine
    0.16
     darin
    0.16
    Activations Density 0.109%

    No Known Activations