© 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. 1197
    Prev
    Next
    INDEX
    Explanations

    divided

    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
     سا
    -0.08
    umsy
    -0.08
     líquido
    -0.08
     Lub
    -0.08
     باش
    -0.07
     sovereignty
    -0.07
     Kaw
    -0.07
     boh
    -0.07
     Hale
    -0.07
     rasmi
    -0.07
    POSITIVE LOGITS
    bass
    0.07
    [type
    0.07
     conjunct
    0.07
    ಡ
    0.07
     निर
    0.07
    วง
    0.07
     quantified
    0.07
    აფ
    0.07
     ch
    0.07
     shattered
    0.07
    Activations Density 0.006%

    No Known Activations