© 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. 102949
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     molto
    -0.09
     firstly
    -0.09
     sedang
    -0.09
     only
    -0.09
     mainly
    -0.08
    など
    -0.08
    -0.08
     récemment
    -0.08
     aðeins
    -0.08
    十分
    -0.08
    POSITIVE LOGITS
     desto
    0.24
     càng
    0.16
    越
    0.12
     kaysa
    0.11
     steigt
    0.11
    akwazi
    0.10
     podrás
    0.09
     будет
    0.09
     semakin
    0.09
     сможете
    0.09
    Activations Density 0.014%
    No Known Activations