© 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. 47274
    Prev
    Next
    INDEX
    Explanations

    GP

    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
    ેર
    -0.08
     prefab
    -0.07
     nuc
    -0.07
    令人
    -0.07
    ута
    -0.07
     combinations
    -0.07
     Agree
    -0.07
     mute
    -0.07
    后一
    -0.07
    াঁচ
    -0.07
    POSITIVE LOGITS
     lanz
    0.09
    ñ
    0.08
    .jface
    0.08
     задерж
    0.08
     결국
    0.08
     schließlich
    0.08
    membership
    0.08
    anish
    0.08
    лана
    0.07
     lanzó
    0.07
    Activations Density 0.000%

    No Known Activations