© 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. 6206
    Prev
    Next
    INDEX
    Explanations

    level

    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
     Seattle
    -0.10
    (over
    -0.10
     Over
    -0.10
     yub
    -0.10
     التفاصيل
    -0.09
     iwwer
    -0.09
    Seattle
    -0.09
    _OVER
    -0.09
     definir
    -0.09
     DEFINE
    -0.09
    POSITIVE LOGITS
     rise
    0.09
     fall
    0.09
     instability
    0.09
     anomalies
    0.08
     standa
    0.08
     unrest
    0.08
    rit
    0.08
    illusion
    0.08
    µ
    0.07
    rise
    0.07
    Activations Density 0.002%

    No Known Activations