© 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. 102826
    Prev
    Next
    INDEX
    Explanations

    cost

    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
     тили
    -0.08
     сумма
    -0.08
     камсыз
    -0.08
    用途
    -0.08
     finalidade
    -0.08
     компон
    -0.08
     aspek
    -0.08
    upuesto
    -0.08
     אליו
    -0.08
     таъмин
    -0.08
    POSITIVE LOGITS
     dearly
    0.13
    lier
    0.09
     costly
    0.09
    liest
    0.09
    liness
    0.09
     adversely
    0.08
     mất
    0.08
     outweigh
    0.08
     losing
    0.08
    مند
    0.08
    Activations Density 0.013%

    No Known Activations