© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68990
    Prev
    Next
    INDEX
    Explanations

    limitations of power

    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
     colspan
    -0.09
    ublin
    -0.08
     Colombia
    -0.08
    roads
    -0.08
    road
    -0.08
    +t
    -0.08
     미국
    -0.08
    uega
    -0.08
    +"_
    -0.08
     Mailing
    -0.08
    POSITIVE LOGITS
    Cooldown
    0.12
     recharge
    0.11
     cooldown
    0.10
     mana
    0.10
     magical
    0.10
     potency
    0.10
    Mana
    0.09
     魔
    0.09
     manifestations
    0.09
    魔
    0.09
    Activations Density 0.024%

    No Known Activations