© 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. 44573
    Prev
    Next
    INDEX
    Explanations

    freeze

    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
    way
    -0.08
    Driven
    -0.08
    Clamp
    -0.08
    sit
    -0.07
     fostering
    -0.07
    Parser
    -0.07
    dut
    -0.07
     unavoidable
    -0.07
    repair
    -0.07
     caut
    -0.07
    POSITIVE LOGITS
    冻
    0.10
    止
    0.09
     autos
    0.08
    冰
    0.08
     �
    0.07
    掉
    0.07
     neut
    0.07
    ification
    0.07
     congel
    0.07
    /free
    0.07
    Activations Density 0.007%

    No Known Activations