© 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. 113487
    Prev
    Next
    INDEX
    Explanations

    positions

    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
     indis
    -0.08
    ovar
    -0.08
     flu
    -0.07
    (tuple
    -0.07
    .unwrap
    -0.07
     merging
    -0.07
    .concat
    -0.07
    (o
    -0.07
    erges
    -0.07
     يعتبر
    -0.07
    POSITIVE LOGITS
    ján
    0.08
     వాళ
    0.08
     presentan
    0.08
     plano
    0.08
    қын
    0.08
    /Layout
    0.07
     जमीन
    0.07
    eft
    0.07
     presentar
    0.07
     दि�
    0.07
    Activations Density 0.004%

    No Known Activations