© 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 EvalsExportsinterp-engineNEWAPI 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. 50427
    Prev
    Next
    INDEX
    Explanations

    say "aland"

    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
     إش
    -0.08
     جذب
    -0.08
     ':'
    -0.07
     vann
    -0.07
     CZ
    -0.07
     הח
    -0.07
                        
↵
    -0.07
              
↵
    -0.07
     virker
    -0.07
    -0.07
    POSITIVE LOGITS
    aland
    0.13
    ppelin
    0.09
    ランド
    0.08
    uwan
    0.08
    倫
    0.08
    漏
    0.08
     refeições
    0.08
    reland
    0.08
    ΠΑ
    0.08
    uguay
    0.08
    Activations Density 0.001%
    No Known Activations