© 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. 110622
    Prev
    Next
    INDEX
    Explanations

    lab experiments

    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
    직
    -0.09
    (strict
    -0.08
    ナー
    -0.07
    ਦੀ
    -0.07
    ാൾ
    -0.07
    (?:
    -0.07
    �
    -0.07
    рет
    -0.07
     valoriz
    -0.07
     stemming
    -0.07
    POSITIVE LOGITS
     reactors
    0.11
     experimenting
    0.10
     experimented
    0.10
     saucepan
    0.09
     assay
    0.09
     Copies
    0.09
     لگا
    0.09
    platte
    0.09
     Experiment
    0.09
     experiment
    0.09
    Activations Density 0.013%

    No Known Activations