© 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. 51384
    Prev
    Next
    INDEX
    Explanations

    arm

    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
     karịa
    -0.08
    פים
    -0.08
    زاد
    -0.07
     Miracle
    -0.07
    ף
    -0.07
     пайда
    -0.07
     plein
    -0.07
     aʻe
    -0.07
    ובר
    -0.07
    тини
    -0.07
    POSITIVE LOGITS
    urerie
    0.20
    strong
    0.17
    aments
    0.16
    oured
    0.16
    ored
    0.15
    ament
    0.15
    ory
    0.14
    chair
    0.14
    ature
    0.13
    aturen
    0.13
    Activations Density 0.012%

    No Known Activations