© 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. 111043
    Prev
    Next
    INDEX
    Explanations

    tags

    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
    oura
    -0.08
     UBS
    -0.08
    RON
    -0.08
     decomposition
    -0.08
     filtr
    -0.08
     βα
    -0.07
    exists
    -0.07
    participants
    -0.07
     infinite
    -0.07
     Mith
    -0.07
    POSITIVE LOGITS
    Substring
    0.09
    贴
    0.08
    ชั่น
    0.08
    Idioma
    0.08
     habilidad
    0.08
    .skill
    0.08
    申请
    0.08
     hockey
    0.08
    Phrase
    0.08
     religión
    0.07
    Activations Density 0.004%

    No Known Activations