© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 31636
    Prev
    Next
    INDEX
    Explanations

    required/mandatory

    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
    UIColor
    -0.08
    wax
    -0.08
    .tint
    -0.07
     хил
    -0.07
    Is
    -0.07
    'Brien
    -0.07
    色
    -0.07
    	Is
    -0.07
    oxi
    -0.07
     spécialis
    -0.07
    POSITIVE LOGITS
     mandatory
    0.18
    mandatory
    0.16
     obrigatório
    0.16
     obligatoire
    0.16
     obligatorio
    0.15
     обязатель
    0.15
     verplicht
    0.15
     obrig
    0.15
     obligator
    0.15
     compulsory
    0.15
    Activations Density 0.096%

    No Known Activations