© 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. 108786
    Prev
    Next
    INDEX
    Explanations

    Android development

    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
     skó
    -0.09
     możliwości
    -0.09
     druk
    -0.09
    _possible
    -0.09
     drukken
    -0.08
     werkzaamheden
    -0.08
     keram
    -0.08
     základ
    -0.08
     aus
    -0.08
     omissions
    -0.08
    POSITIVE LOGITS
    Autowired
    0.10
    VO
    0.09
    -view
    0.09
    /view
    0.09
    Observable
    0.08
    /state
    0.08
    (view
    0.08
    Mutable
    0.08
    Father
    0.08
    .viewmodel
    0.08
    Activations Density 0.002%

    No Known Activations