© 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. 3-RESID-POST-AA
    11. 2853
    Prev
    Next
    INDEX
    Explanations

    Spicy food

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    öße
    -0.09
     impr
    -0.08
     frosting
    -0.08
    cust
    -0.07
    iële
    -0.07
    /load
    -0.07
     freer
    -0.07
    əmə
    -0.07
     foment
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     Mach
    0.09
    Mach
    0.08
     Micros
    0.08
    Bud
    0.07
     Micro
    0.07
     Blacks
    0.07
     Jornada
    0.07
     bud
    0.07
    autor
    0.07
    790
    0.07
    Activations Density 0.002%

    No Known Activations