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

    Neuronpedia

    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. 3-RESID-POST-AA
    11. 994
    Prev
    Next
    INDEX
    Explanations

    年来

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     заст
    -0.09
    urge
    -0.08
    lsl
    -0.08
     �
    -0.08
     stimmt
    -0.08
     Judah
    -0.08
    uper
    -0.07
    داد
    -0.07
    avis
    -0.07
    adec
    -0.07
    POSITIVE LOGITS
     sing
    0.07
     condu
    0.07
     ENTRY
    0.07
     exemplary
    0.07
     coronavirus
    0.07
    ENTRY
    0.07
    	row
    0.07
     ambulance
    0.07
    -row
    0.07
    имент
    0.07
    Activations Density 0.000%

    No Known Activations