© 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. 71094
    Prev
    Next
    INDEX
    Explanations

    HTTP 5xx errors

    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
     Lavender
    -0.09
     Nylon
    -0.09
     Allah
    -0.09
     homogeneous
    -0.08
     lavender
    -0.08
     euch
    -0.08
     Nairobi
    -0.08
     Burundi
    -0.08
     they
    -0.08
     dear
    -0.08
    POSITIVE LOGITS
     phạm
    0.08
    fault
    0.08
     throwable
    0.07
     drugs
    0.07
    Fault
    0.07
     Fault
    0.07
     руками
    0.07
     Validators
    0.07
    年代
    0.07
     воз
    0.07
    Activations Density 0.001%

    No Known Activations