© 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. 71139
    Prev
    Next
    INDEX
    Explanations

    story writing instructions

    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
    -0.08
    Coords
    -0.08
     chut
    -0.07
     pru
    -0.07
    стру
    -0.07
     sentencia
    -0.07
    �र
    -0.07
     mates
    -0.07
     cran
    -0.07
     koju
    -0.07
    POSITIVE LOGITS
     början
    0.08
    局
    0.08
    -front
    0.08
     intimid
    0.08
    YEAR
    0.07
     జరుగ
    0.07
    -Nov
    0.07
    Astr
    0.07
     anfangen
    0.07
    域
    0.07
    Activations Density 0.011%
    No Known Activations