© 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 EvalsExportsAPI 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. 49754
    Prev
    Next
    INDEX
    Explanations

    under

    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
    essed
    -0.08
    imated
    -0.08
    ected
    -0.07
     subsequent
    -0.07
     observed
    -0.07
     experienced
    -0.07
    hibited
    -0.07
     risk
    -0.07
     evaluation
    -0.07
     observation
    -0.07
    POSITIVE LOGITS
    p
    0.20
    curr
    0.13
    pin
    0.12
    klady
    0.10
    PIN
    0.10
    .curr
    0.10
    bel
    0.10
     p
    0.10
    pell
    0.10
    pdata
    0.10
    Activations Density 0.003%

    No Known Activations