© 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. 48529
    Prev
    Next
    INDEX
    Explanations

    per or hyphen

    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
     destruct
    -0.10
     uphe
    -0.10
     verabsch
    -0.09
     departing
    -0.09
     descend
    -0.09
     Departure
    -0.09
     downturn
    -0.09
     normalize
    -0.09
     satisfaire
    -0.08
     afscheid
    -0.08
    POSITIVE LOGITS
     detection
    0.19
     prevention
    0.17
    Detection
    0.16
    _detection
    0.16
     Detection
    0.15
    -pre
    0.15
    -resistant
    0.15
     Prevention
    0.15
    检测
    0.14
    -proof
    0.14
    Activations Density 0.020%

    No Known Activations