© 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. 23-RESID-POST-AA
    11. 97459
    Prev
    Next
    INDEX
    Explanations

    warriors and swords

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naments
    -0.09
     Monsieur
    -0.08
     Samstag
    -0.08
     gebouwen
    -0.08
    _arch
    -0.08
     architectures
    -0.08
     frameworks
    -0.08
    yond
    -0.08
    plements
    -0.08
    יין
    -0.08
    POSITIVE LOGITS
     siger
    0.08
     editorial
    0.08
     pressão
    0.08
    战略
    0.08
     war
    0.08
     feng
    0.08
    ográfica
    0.08
    .track
    0.07
     battle
    0.07
     pressure
    0.07
    Activations Density 0.006%

    No Known Activations