© 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. 11-RESID-POST-AA
    11. 110456
    Prev
    Next
    INDEX
    Explanations

    Comparing A, B, and C

    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
     cose
    -0.07
    uert
    -0.07
     isn't
    -0.07
     беру
    -0.07
     thank
    -0.07
    弊
    -0.07
     ;-
    -0.07
    Tun
    -0.07
    ியாக
    -0.07
    励
    -0.07
    POSITIVE LOGITS
    �
    0.09
    ◇
    0.09
     यांच्या
    0.08
     monaster
    0.08
     gard
    0.08
     фонда
    0.07
     pian
    0.07
    ABB
    0.07
     Surround
    0.07
     �
    0.07
    Activations Density 0.028%

    No Known Activations