© 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. 110903
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
     җәм
    -0.08
     Җ
    -0.08
     े
    -0.08
     Bek
    -0.08
     bene
    -0.08
     �
    -0.08
    Ու
    -0.08
     खातिर
    -0.08
     edýän
    -0.07
    �读
    -0.07
    POSITIVE LOGITS
    综合
    0.08
     conclu
    0.08
     estabele
    0.07
     综合
    0.07
    anked
    0.07
     établ
    0.07
     employing
    0.07
    .land
    0.06
     pien
    0.06
     concluding
    0.06
    Activations Density 0.001%

    No Known Activations