© 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. 11-RESID-POST-AA
    11. 69567
    Prev
    Next
    INDEX
    Explanations

    iceps

    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
     unob
    -0.07
    icked
    -0.07
    gef
    -0.07
     hillside
    -0.07
     gv
    -0.07
     sopa
    -0.07
     undocumented
    -0.07
     vp
    -0.07
    astream
    -0.07
     uppsk
    -0.07
    POSITIVE LOGITS
     ideas
    0.08
     assuntos
    0.08
     spécialiste
    0.08
     Ideas
    0.08
     Idee
    0.08
     ideias
    0.08
                    ↵
    0.08
    =max
    0.08
     Ideen
    0.07
    重点
    0.07
    Activations Density 0.002%

    No Known Activations