© 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. 619
    Prev
    Next
    INDEX
    Explanations

    the

    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
     vigilant
    -0.08
     vigilance
    -0.08
    ölle
    -0.08
    rogate
    -0.07
     πί
    -0.07
    escape
    -0.07
     Escape
    -0.07
     Pompe
    -0.07
    unter
    -0.07
    ,out
    -0.07
    POSITIVE LOGITS
     professora
    0.08
    קד
    0.07
    īb
    0.07
     czerw
    0.07
     csrf
    0.07
     nug
    0.07
    ীদ
    0.07
     COS
    0.07
     madres
    0.07
     tutors
    0.07
    Activations Density 0.033%

    No Known Activations