© 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. 63218
    Prev
    Next
    INDEX
    Explanations

    Grabbing/catching/holding

    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
     duidelijke
    -0.07
    idog
    -0.07
    doors
    -0.07
     খ
    -0.07
     delicioso
    -0.07
     indoor
    -0.07
    Describe
    -0.07
     doors
    -0.07
    _sz
    -0.07
     taxable
    -0.07
    POSITIVE LOGITS
    oja
    0.09
     humanidade
    0.09
    atchewan
    0.08
    čil
    0.08
     Mature
    0.08
    ుకుని
    0.08
     Hust
    0.08
     chứng
    0.08
    ેથી
    0.08
    ────────────────
    0.08
    Activations Density 0.004%

    No Known Activations